Datarim — Changelog

v2.66.2

Latest August 13, 2026

FIX Hard-gated autonomy enforcement. Automatic policy decisions now honour the configured hard-gate list first, failing closed when the hard-gate configuration is missing or malformed.

v2.66.1

August 13, 2026

CHANGE Framework-batch reconciliation. The current-main-adjudicated framework residue is now the canonical tree; superseded rescue branches were retired after exact-main verification.
FIX Shared-mode pre-archive schema reachability. The schema gate now runs after per-file hunk attribution and before every shared-mode return, so own, mixed, or unattributed dirty state cannot mask malformed ledgers. The explicit --no-schema-check escape remains unchanged.

v2.66.0

August 12, 2026

FEAT Module manifest gate. dev-tools/check-module-manifest.sh validates a module.yaml bundle descriptor (schema version, semver, kebab-case id, non-empty skill list, per-skill summary, requires), with a shipped example template and a reference doc.
FEAT MCP server for the Datarim catalog. cli/mcp/datarim-mcp-server.sh exposes commands, skills and agents over MCP (list / resolve / body, path-confined, size-capped); a registrar writes [mcp_servers.datarim] into ~/.codex/config.toml, wired into install.sh (--no-codex-mcp opts out).
FEAT Three review skills split out of the monolithic adversarial pass — adversarial-review (break the artifact), edge-case-hunter (boundary and degenerate inputs), structure-review (does the document hold together). Loaded at the /dr-plan Transition Checkpoint and /dr-qa. Skill count 69 → 72.
FEAT Preflight caller contract enforced — the composite preflight action validates its caller's inputs against consumers.yml, exposes the notification outcome as an explicit output, and reports timesync state with a measurable offset.
CHANGE Telegram article publication contract. An article is exactly two sequential ordinary channel posts in one chat — media plus bold title, then title plus full text plus a single linked CTA — with no comment/thread routing and a read-back gate over both returned ids. The channel-comment recipe stays documented for non-article posts.
FIX Reserved-prefix shadowing is reported instead of applied silently. A project registry row repeating a universal area prefix (DEV, QA, …) was discarded with no output, stranding archives outside the corpus later searches cover; the doctor now emits a WARN naming both the reserved and the ignored value. Resolution precedence is unchanged.
FIX Pre-archive schema gate is reachable, and the indent bypass is closed. The gate ran only when every repo was clean, so any dirty repo skipped it; it now runs unconditionally. The violation scan anchored at flush-left bullets, exempting indented rows; indented rows are now held to the same shape. Both fixes are mutation-tested.

v2.65.0

August 9, 2026

FEAT Prefix-agnostic task-ID provenance gate. The history-agnostic scanner now covers public runtime instructions, four public documentation categories, root entry documents, and five shipped text extensions, with exact path exemptions, portable lexical boundaries and NUL-safe traversal closing the previous silent bypasses. The public-site contract now rejects every generic task prefix instead of maintaining a closed list.
FEAT VERSION↔tag parity gate. A blocking CI job fails when the version declared in VERSION has no matching tag on origin — the silent half-release (bumped manifest, never-pushed tag, no artefacts) that two earlier cuts fell into.
FEAT Runtime drift check. check-runtime-drift.sh fails when the agent runtime symlinks into a checkout sitting on a feature branch or detached off any release tag — the state where every agent on a host silently serves stale rules. Wired as a blocking step in validate.sh.
FIX Closure-gate false block. Fixed-string verification via git grep -F broke on patterns containing a literal \E; verification now pipes the base tree to GNU grep in a two-pass batched scan (minutes → ~15 s), with substring semantics unchanged.
FIX /dr-quick emitted a malformed tasks.md row — the step now shows the exact line to emit instead of naming field values as prose, and a deferral-prose line-scoped false positive is corrected. The v2.64.0 release was completed retroactively with its annotated tag and release run.

v2.64.0

August 5, 2026

FEAT rotation-runbook skill. Credential-rotation playbook distilled from three real rotation exercises: consumer inventory with a secret-store↔producer truth-check, deliberate grace-window choice, auth-scoped revoke/issue verification (the false-green trap), full producer-payload replay over a minimal probe, canonical secret-store path discipline, a rotation-log entry, and leak-response addenda. Skill count 68 → 69.
CHANGE Outsider-friendly English pass on the shipped surface. Residual paraphrasable Russian prose behind allow-non-ascii markers is now English; framework jargon (FB rules, verifiable acceptance criteria, Class A/B proposals) is defined on first use with definition links; circular self-links removed. Canonical operator-output tokens and content-work skills keep their Russian by policy.
FIX CI supply-chain repin. The rust-toolchain action pin was orphaned by an upstream rebase and tripped the impostor-commit audit on every PR; repinned to the live stable SHA.

v2.63.0

August 4, 2026

FEAT TDD-enforcement toggle plugin. Core-owned, metadata-only, default-on plugin with a stateless workspace resolver and a tombstone “Disabled Defaults” contract; dr-plugin doctor gains a tenth health check.
FEAT Agent frontmatter gate. New blocking CI job validates agent frontmatter schema (and wires the previously-unwired skill frontmatter check).
FEAT Narrative-parity dimension for the repo↔site drift detector, plus a release environment policy-as-code file with a live drift advisory.
FEAT Anti-decay regressions for the pre-push local-validator wiring and the /dr-plan stdlib-symbol advisory, plus a wiki raw-content semantic orphan check.
FIX next-free-id.sh fails closed on a ledger-less root; framework hygiene: tracked documentation/ was gitignored — rule removed, reassert lint promoted to its own blocking CI job; skill-count drift in shipped docs corrected.
CHANGE PRD-amendment sidecars decision recorded (deliberately not landed; permanent rejection ADR) and the fb-rules one-cycle deprecation copy retired.

v2.62.0

August 3, 2026

CHANGE Backlog schema fork superseded. The later field-proven backlog contract already permits a single-line inline pending-work description without a task-description pointer, while the active-task index and the active-context mirror retain required pointers. The system skill, the doctor skill, and the backlog template now match the canonical regex split in the shared schema library; a focused regression pins both sides without changing doctor runtime behaviour.

v2.61.0

August 2, 2026

FEAT Archive-landing truth gate. Direction A checks archive artefact paths and cited commits against the content actually present on the verification ref, distinguishing removed, moved, foreign, unverifiable, and squash-landed evidence. Direction B is an advisory stale-label scan for open backlog rows. The gate is scope-guarded against cross-repository false verdicts, reports undated archives instead of guessing dates, and ships 16 focused test contracts including mutation coverage. It is wired into the framework gates, and the template-path gate is now enforced by CI.
FIX Relanded the snapshot task-ID regex fix. Slug-suffix follow-up IDs remain resumable after the archived change was recovered and landed under a squash merge.

v2.60.1

August 2, 2026

FIX The snapshot size cap no longer silently disarms on macOS. An oversized options file makes the frontmatter alone consume the whole 8192-byte cap, so the body budget is deliberately clamped to zero — but the zero-byte truncation relied on a GNU-only byte-count behaviour that BSD/macOS rejects with an error. Under strict mode that aborted the writer before the cap check could fail closed, converting a hard guard into a silent pass while Linux-only CI stayed green. The zero case is now an explicit truncate, and the regression test is mutation-verified.
FEAT Wrapper-level snapshot regressions. New coverage for the frontmatter/body separator (an ordinary body without a leading newline must not glue to the terminator) and for the decimal-width boundary of the declared byte size.

v2.60.0

July 31, 2026

FEAT Release-ledger drift gate. A new read-only report fails when the framework version was bumped but the matching changelog section was never cut. Version boundaries are derived from the version-header history rather than hardcoded; report mode prints the commit and pull-request mapping, bullet mode attributes unreleased entries to their real version, and check mode requires zero orphaned commits and zero undocumented versions.
FEAT The closure gate now verifies the ledger as well as the code. A task could previously reach the main branch without ever gaining a row in the active or pending index and still pass closure. The gate now requires an anchored row beginning with the exact task ID, rejects citation-only and prefix-collision matches, supports an explicit ledger path and a fail-closed require-ledger mode, and remains backwards-compatible for repositories with no Datarim ledger.
FEAT Interactive task-spec wizard — /dr-wizard + the wizard skill + a pure-bash state engine. Evolves the linear discovery → /dr-prd chain into a guided, one-question-at-a-time, tree-drilling interview that co-authors a PRD with the operator. State is an append-only JSONL event log per task whose current value is a projection over events — resumable by replay, branchable by a derived drill-stack. Operators can drill into a hard sub-question in a nested side-thread and pull the conclusion back without carrying a manual session id (context captured as references, not copies), convene a consilium on demand, and mark mid-flow re-scope through dirty flags (tracking only in v1 — the re-plan stays operator-confirmed). A knowledge/dependency graph is emitted as a documented ingestion contract with node labels redacted at the outbound sink boundary. /dr-prd gains a finalized-gated, idempotent consume-hook; the plain discovery path is unchanged when no wizard artefact exists.
FEAT Cross-KB evolution digest, read at /dr-archive Step 0.5. Self-evolution runs per knowledge base, so when a task in a non-framework KB evolves the shared runtime the lesson lands in that KB’s log and never reaches the operator watching the framework KB. A new strictly read-only tool merges per-KB evolution logs into one source-tagged digest with two buckets — framework changes already made elsewhere (not to be re-proposed) and project-local lessons that may warrant promotion. Rows are treated as untrusted data throughout: never evaluated, never sourced, never opened as a path. No KB is ever silently absent — each root renders an explicit OK / missing-root / no-log / empty / parse-error / stale status.
FEAT Plan-time seam-vs-integration boundary detector, plus the matching skill. /dr-plan had mandated this check for L3–L4 in prose only. The tool half is now shipped: a narrow, deterministic, advisory scanner that flags a backlog one-liner bundling a seam/contract concern (define an interface or dispatcher in one module) with an integration/call-site concern (wire it into a caller elsewhere). It exits clean whether or not it flags, so it never blocks a plan, and its signal lists are documented as a floor rather than a ceiling — a pass does not discharge planner judgement.
FEAT Task-ID collision hardening — atomic claim, reservation mutex, and a cross-instance advisory. Three independent windows are closed. A directory-based lock makes the /dr-init claim itself atomic, so of two concurrent sessions exactly one wins and the other bumps and retries; the id selector now atomically reserves the chosen id before printing it, adding a fourth claim surface alongside archive, active-task index, and backlog; and a read-only probe reports an id already claimed in a sibling instance (workspace root versus a nested project tree), which previously went unnoticed and caused a three-way collision. Markers are gitignored runtime state and self-expire on a configurable TTL.
FEAT Frontmatter-key mirror drift guard. A machine-readable contract that is not mirrored to a human-readable surface next to its call site decays silently, and existing checks did not cover it — one validates frontmatter shape, another validates its language. A new read-only two-pass guard, fed by a shipped key registry, verifies that every live top-level frontmatter key across commands, skills, and agents is categorised, that no live entry has vanished, that no reserved key appears live, and that keys requiring a mirror co-occur with their body marker in both directions. Runs as its own blocking workflow.
FEAT Collision-safe task-prefix rename tool. The rename policy said «update all references atomically» and shipped no way to do it, while a task token is indistinguishable by regex from a homograph such as an ADR number — one blind sweep had already corrupted cross-references across a document set. Every token now passes through a pure, offline, anchored classifier: an exclude-anchor protects a whole line, and for numbers listed as colliding a token renames only when an include-anchor is also present. Anchors are compared as literal substrings, never compiled as patterns. Dry-run by default, with opt-in apply, file rename, and a verify pass that fails on half-rename residue.
FEAT Cross-runtime /dr-auto activation smoke, wired blocking. Verifies the runtime-agnostic activation claim mechanically rather than by prose: that the marker is written and resolved so the question-suppression ladder engages off the marker and not off runtime identity; that a spawned subagent is classified correctly with the environment variable unset, since it does not inherit the parent shell; and that the hard-gated action list is non-empty. Complements the existing prose linter by exercising the primitives.
FEAT Gated local archive auto-commit. /dr-archive can capture a globally clean repository boundary and commit only the task’s archive document plus an optional final snapshot, through hook-free plumbing. Default-off, with foreign-change refusals and an explicit skip preserving shared-workspace safety. No remote, tag, release, or version action is ever performed.
FEAT Framework version accountability. /dr-init now records an immutable repository baseline. For shipped framework behaviour, /dr-do and /dr-qa independently require either a version-and-changelog update or a committed, task-bound release deferral, preventing a version bump from drifting away from its release evidence.
FEAT Brand-hygiene policy for absorbed external skills. The evolution contract now requires provenance attribution, replacement of source-brand cross-references with Datarim equivalents, removal of undeclared external path interoperability, and a regression-gate extension for every newly absorbed source brand.
FEAT Partial Milestone Closure Pattern for autonomy milestones spanning several child tasks. New shipped-surface contract documenting how one milestone is closed incrementally across two or more children: the parent append-log schema for partial and full closure entries, the closed/deferred status word set, the responsibility split (the parent owns the ledger; only the last closing child performs the level bump), and reopen-on-fallback semantics that revert a bump when a closed component regresses.
FEAT Audit-log adapter and redaction layer for fleet skill evolution. A third source adapter reads the optional fleet audit stream and emits one evaluation record per entry through the shared JSONL contract. Every reason and trace is redacted before it can reach an external model; the adapter self-skips when its broker is unavailable, and the evolution loop now recognises broker URLs without applying filesystem-path checks to them.
CHANGE Coworker-delegation mandate now exempts vetted architectural design docs. The written policy lagged already-shipped, already-tested runtime enforcement: the guard silently allowed a design document whose name matched an exemption glob, while the mandate text still listed design docs as unconditionally delegated. The exemption is now stated and gated on a four-condition conjunction — the document records a decision rather than a first-time exploration, its facts were vetted in-cycle, those facts are correctness-critical, and the specification already approximates the final text. No hook behaviour changed.
CHANGE Secrecy-aware project scaffolding. When the operator brief carries a secrecy signal, /dr-init now scaffolds in secrecy-aware mode: mechanism-bearing reference stubs are written with redaction placeholders, the public documentation surface and README are forbidden from carrying mechanism vocabulary, and a secrecy declaration plus a grep gate is emitted into the project instructions at scaffold time rather than as a post-hoc repair. The non-secret scaffold path is byte-identical to before.
FIX The release ledger and version file no longer disagree. The version had advanced through six releases while the changelog stopped at 2.53.0. The linear version-header history supplied exact boundaries, so all 158 commits in the window were partitioned with zero orphans and the 40 accumulated entries were attributed to the versions that introduced them: 10 / 1 / 1 / 1 / 3 / 4 / 20 for 2.54.0 through 2.60.0. All 210 pre-existing changelog entries remained byte-identical after redistribution.
FIX Cross-KB digest determinism test no longer flakes at a one-second boundary. The assertion compared two runs while their status blocks included a wall-clock-derived age, so otherwise identical output could differ when the calls straddled a second. The test now pins the tool’s documented clock hook and verifies the intended global ordering property.
FIX The seam-boundary skill now resolves its validator from the installed runtime. A bare relative developer-tools path worked only from the framework repository and broke in consumer projects. The command is now runtime-qualified, and the path-convention detector is included whenever new shipped instructions name a developer tool.
FIX /dr-init no longer hard-fails for framework tasks on a default-umask host. The version-accountability pair guarded the repository root with the predicate written for the record directory it creates, which additionally forbids the group-write bit. Under the common default umask every checkout is group-writable, so the baseline capture exited with an unsafe-repository error on an ordinary clone — and because that exit is declared a hard init failure, /dr-init was blocked outright for every framework task on such a host. The repository root is only ever read, so it now uses the same guarantee applied elsewhere: owned by us, not a symlink, not world-writable. The stricter rule still guards the record directory.
FIX Recovered documentation lost when duplicate reland pull requests were closed. Three gates were relanded twice in parallel and the first set merged, closing the others. A file-path comparison said nothing was lost, but a content comparison found two deltas: the developer-tools catalogue was missing rows for six newly landed tools, and the multi-runtime guide had lost an operator-facing section. Both are restored, with one correction — the continuous-integration wiring is a blocking job, not the advisory arrangement the closed branch described.
SECURITY Personal identifiers removed from the shipped surface. The pre-release audit removed personal home paths, internal machine names, routable addresses, and operator-authored init-task records from tracked public files. Public references now use placeholders, the plugin attribution matches the project licence, and ignore rules cover task-intake records, insights, and environment files. No live credential was found.

v2.59.0

July 30, 2026

NOTES Reconstructed release notes. This version was bumped in the framework version header but never cut as a changelog section at the time. The entries below were recovered retroactively during the 2.60.0 release audit by attributing each unreleased entry to the commit that introduced it. 27 commits landed in this range — the entries listed are those that carried a changelog entry, not the full commit set.
SECURITY New rule cluster S11 — untrusted-content boundary review gate. A distinct adversarial security review becomes a mandatory pre-merge gate whenever a change implements or modifies a boundary where untrusted bytes enter a model context: retrieved knowledge-base documents, fetched web or tool output, user files, any external corpus rendered into a prompt or tool result a model reads. A green build alone does not clear it — the automated jobs do not model prompt-injection semantics. The review is findings-only, run by a reviewer in a context separate from the implementer, and must probe fence-escape, nonce-predictability, trust-class cross-promotion, provenance-forgery, size-guard bypass, and fail-open behaviour.
FEAT Regeneration of the execution-host map from canon. The machine-local map the runtime guard consults was hand-maintained, so a stale or missing map degraded to fail-open and let commands run locally even where a required-host binding exists. The documented repair flag was declared in the script header but never implemented; it now upserts the binding from the committed canon and stamps a sync time, making the local map a derived artefact. Canon owns host identity, the local cache owns the machine-local workspace path, and the operation is idempotent and isolated from other bindings.
FEAT Execution-host routing resilience. Three hardenings. A session-start advisory reports canon-versus-cache drift, staleness, or a missing cache in one line and never blocks. A canon-fallback resolver reads the space definition directly when the cache has no binding, so «unconfigured» now means canon truly has no execution mandate rather than «cache absent on a host that should be gated»; that also makes the flip to fail-closed safe, since mutating intent whose host cannot be resolved is denied while read-only intent stays fail-open. And the machine-local guard now catches raw branch and worktree creation shapes when off-host, while deliberately excluding plain commits and read-only operations so the operator’s own close-out flow is not broken.
CHANGE /dr-quick off-host routing now distinguishes read-only from mutating intent. Every off-host quick task was previously treated as observational and always ran locally, so a mutating one edited files and switched branches on the operator’s laptop in violation of the execution-host mandate. A genuinely read-only task still stays local and surfaces the delegation directive as information only; a mutating one auto-dispatches to the required host. Because a quick task’s intent is only settled mid-flow, the dispatch decision is deferred and re-evaluated, with a guard so a lookup that turns into a mutation dispatches before any local change.

v2.58.0

July 22, 2026

NOTES Reconstructed release notes. This version was bumped in the framework version header but never cut as a changelog section at the time. The entries below were recovered retroactively during the 2.60.0 release audit. 5 commits landed in this range — the entries listed are those that carried a changelog entry, not the full commit set.
SECURITY Fail-closed public repository boundary and build-execution evidence gates. New read-only helpers verify an exact allowlisted file tree plus all reachable history against redacted-path policy and live secret scanning, and separately distinguish an actually executed, successful, required job on the exact commit from no execution, pending, failed, mismatched, or indeterminate evidence. The planning, compliance, and archive commands now require these gates when their trigger conditions apply.
FIX Deploy-class classifier fails loud instead of fail-open on caller and input-output errors. Two paths silently resolved to «not deploy-class, gate skipped»: a flag given without a value crashed argument shifting under strict mode, and an existing but unreadable task description masked the read error inside a pipeline without failure propagation. Both now exit as usage errors with a message on standard error.
FIX Deploy-class classifier no longer arms on negated prose. Indicator tokens were matched as substrings anywhere in the task description, so a narrative disclaimer such as «this task does not touch the unit manager» falsely armed the pre-archive production-merge gate on a non-deploy task. Indicator hits now pass through a negation-marker line filter that is deliberately minimal and fail-safe — unmatched phrasings leave the gate armed. The changed-paths surface is unaffected.

v2.57.0

July 15, 2026

NOTES Reconstructed release notes — thin section. This version was bumped in the framework version header but never cut as a changelog section at the time, and was recovered retroactively during the 2.60.0 release audit. 1 commit landed in this range and carried the single entry below; this is the complete set for this version.
CHANGE Off-host delegation is now autonomous, with no operator round-trip. The execution-host contract previously told an off-host agent to emit a delegation directive and stop; it now auto-dispatches for mutating pipeline stages and the autonomous driver, on the reasoning that the required-host binding is the operator’s standing authorization and that dispatch is reversible transport while irreversible steps remain hard-gated on the remote agent. Read and utility stages stay local and never dispatch. Guards: attach to an existing session rather than relaunching; host-key pinning replaces the removed human check on the target; an off-host verdict has exactly two outcomes, remote dispatch or stop-and-report, with local execution never an outcome and a corrupted map failing closed; a bare task-id payload only; and a read-only monitor with a first-status deadline, a single re-send, and escalation rather than silent re-dispatch.

v2.56.0

July 15, 2026

NOTES Reconstructed release notes — thin section. This version was bumped in the framework version header but never cut as a changelog section at the time, and was recovered retroactively during the 2.60.0 release audit. 1 commit landed in this range and carried the single entry below; this is the complete set for this version.
SECURITY Branch-integration floor — a pre-tool-use hook that hard-blocks unreviewed integration. Any direct merge or push of an integration branch into a protected branch is blocked; the only path to a protected branch is feature branch → pull request. Injection-resistant by construction: it reads only the structured command, strips heredoc and quoted bodies, and no environment variable, flag, or in-band text disables it. Fails closed on an ambiguous head. Blocks merge, push, and rebase shapes including force refspecs and the compound checkout-then-merge form, while read-only look-alikes and reverse pulls of a protected branch into your working branch pass.

v2.55.0

July 14, 2026

NOTES Reconstructed release notes — thin section. This version was bumped in the framework version header but never cut as a changelog section at the time, and was recovered retroactively during the 2.60.0 release audit. 1 commit landed in this range and carried the single entry below; this is the complete set for this version.
FEAT Dispatch monitoring layer. A delegated agent now writes a synced heartbeat status file, and the monitoring side reads it to disambiguate a bare remote prompt. A classifier joins pane liveness with status freshness into a read-only verdict — running, awaiting, stalled, done, dead-orphan, or hold — with safety invariants: an awaiting-operator task is never reaped, a live child blocks a dead-orphan verdict, and a dead-orphan requires at least two consecutive stale probes. An aggregator reports all status files at once, pinning actionable states first and flagging stale syncs so a task is never falsely reported as done.

v2.54.0

July 14, 2026

NOTES Reconstructed release notes — substantially incomplete. This version was bumped in the framework version header but never cut as a changelog section at the time, and was recovered retroactively during the 2.60.0 release audit. 77 commits landed in this range and only the nine entries below carried a changelog entry — this is a partial record, not the full commit set.
FEAT Shared execution-host resolver library. One sourceable resolver with no side effects, serving two consumers: a new step-zero execution-host block in the executional commands, and the machine-local pre-tool-use guard, which now sources the library and falls back to its embedded logic when the library is not yet installed on a given machine. Contract: resolve the workspace root, look up a binding, match the host, and return a verdict — on-host or unconfigured, off-host and delegate, or fail-closed on malformed configuration.
FEAT Step-zero execution-host contract across the executional commands. After the existing path-resolution step, each command now consults the resolver and emits a delegation directive on an off-host verdict, otherwise proceeding unchanged and failing open when unconfigured. This is the cooperative soft layer; the machine-local hook remains the hard floor.
FEAT Standalone execution-host drift validator, plus a doctor scope that consumes it. Compares the committed canon against the machine-local binding for the same space and reports time-to-live staleness. Canon always wins and the validator only reports, never rewriting canon. The doctor’s new scope merely invokes the standalone tool and aggregates findings, keeping the comparison logic out of the migrator per the framework’s orthogonal-tools rule. A local-repair flag documents and audit-logs that the doctor may run on the control machine even inside a bound workspace.
FEAT Recorded-fixture tests for thin HTTP wrapper clients. A new testing gate mandates that a wrapper capture one real response into a fixtures document before implementation, that its spec include at least one integration-style test asserting against that recorded response rather than a synthetic stub, and that the spec decode through the real schema so a response-shape drift fails the test.
FEAT Semantic-orphan check for raw knowledge-base captures. A new advisory-only doctor pass flags a file whose name shares no meaningful token with the opening of its content — a signal of an accidental paste into the wrong file. Report-only; the repair mode does not touch the raw tree.
FEAT Legacy-hardware probe checklist template. A seven-step probe for legacy embedded integrations — processor architecture, tunnel device, free memory, key-derivation support, shell applet availability, scheduler spool permissions, and machine-identity sources — run before committing to an architectural approach, replacing speculative toolchain assumptions with a short probe.
FEAT History-agnostic runtime-body probe moved left into plan review. The gate rejecting task-id provenance in shipped skill, agent, command, and template bodies now runs at plan time rather than only at review and hardening. When implementation steps name a runtime body as an edit target, the planner dry-runs the gate against the cited paths and any example text it will ship, and resolves every cited path through the existing exists-and-deprecation ladder — reusing both gates rather than re-deriving them.
FEAT Installer syncs the delegation fragment into the operator’s personal instructions file. Mirrors what the other runtime already did, but for a hand-maintained personal file only the block between sentinel comments is replaced — everything else is preserved byte-exact. Idempotent, and fail-soft when the sentinels are absent or the file does not exist; the installer never creates or reformats an operator’s personal file.
CHANGE Repository-root installer scripts scrubbed of task-id citations. The install, update, and validate scripts carried roughly thirty inline provenance citations, which the history-agnostic gate does not cover for root shell scripts. Citations were replaced with the version anchors already present alongside most of them, or generic phrasing where no anchor existed. Two occurrences are intentionally untouched: a backup filename suffix and a backup glob are literal on-disk naming tokens matched against backups created by earlier installer runs, and renaming them would break restore compatibility.

v2.53.0

July 10, 2026

FEAT Automatic post-step self-verification hook wired into the requirements, planning, and implementation stages. After every one of those stages the command now runs the tri-layer self-verification contract automatically — the pipeline-integrated counterpart of the manual verify command, reusing the same skill. Dispatch is complexity-tiered: the smallest tasks skip the hook because the overhead exceeds the value, mid-size tasks run the deterministic floor plus a single peer-review agent, and larger tasks add the three-way parallel native dispatch across reviewer, tester, and security. Advisory and findings-only by default, with an opt-in hard mode and a kill switch.
FEAT Coworker type-signature mirror guard. When a delegated draft cites types or variants from a canonical source, the specification must now carry a verbatim canonical block, an exact-mirror instruction, and a post-generation grep pass, enforced by a new linter. Prevents fabricated type signatures reaching an artefact.
FEAT Fleet router entry added. The five level fragments previously had no top-level skill file, which failed the skill-layout check.
FIX Coworker context file-type gate documented accurately. The delegation fragment claimed write paths had no allowlist; corrected to describe the code gate on context files, the target-only exemption, and the self-recursion workaround for documentation generation.
FIX Orchestrator context-window self-clearing. Default-off adapters now checkpoint the active task description and the completed snapshot phase before a fixed compact or clear instruction, then use snapshot-first resume for continuity. Taught labels remain data-only, and same-user runtime trust requires explicit opt-in.

v2.52.0

July 10, 2026

FEAT Confirmed auto-learning in the orchestrator. A successful trusted resolution can emit an actor- and session-bound «save as rule?» callback. An affirmative one-time confirmation persists an exact learned match with 24-hour re-validation and an immutable seven-day expiry; learned actions remain subject to per-space policy and to the hard-gated floor that never auto-executes.
FEAT New skill: image-prompting. A reusable playbook that turns a content brief into a precise, repeatable prompt for instruction-following image generators (the gpt-image family and equivalents) — blog covers, video thumbnails, social-post visuals, illustrations, infographics, logo marks, and edits of existing images. Covers the full method: intake → spec → prompt → verify loop, prompt anatomy, composition, style/medium, camera/lens, light, mood, palette, text-in-image constraints, negative constraints + invariants, native aspect/size handling for gpt-image-style tools, and iterative refinement. Ships a prompt-templates.md fragment with nine fill-in-the-blank templates and a ship-readiness verification checklist. Wired into the writer and editor agents and the agent↔skill dependency map.
CHANGE Skill registries synced to 60 skills across CLAUDE.md, README.md, and the skills reference; the "with supporting fragment directories" count corrected to its live value (13) with an inline definition, and /dr-addskill gained an all-occurrences count-sync reminder.
FIX English-only shipped surface passes cleanly. Canonical non-English schema and section names cited verbatim in the expectations-checklist skill, and the localized text-normalization examples in the publishing skill (a content-work skill), are now wrapped in explicit allow markers, so the language validator reports a pass across the whole commands, skills, and agents surface without relying on its advisory tolerance.

v2.51.1

July 9, 2026

FIX Codex skill fanout is atomic. The installer now builds generated skill adapters in a staging directory and swaps the completed tree into place, preventing transient missing-skill startup warnings when the runtime launches while the installer is regenerating wrappers.
FIX Codex skill wrapper source paths point at nested skill files. Generated adapters now reference the real nested path for each skill instead of an invalid flat one, making diagnostics and manual source lookup accurate.

v2.51.0

July 8, 2026

FIX Coworker model routing is split by task semantics. Runtime delegation now uses a documentation-read profile and a classifier profile on a fast model for literal extraction and short routing only, while meaningful draft generation uses a dedicated write profile on a stronger model.
FIX Adversarial verification no longer routes through the external delegate. The verify command rejects external coworker providers; acceptance-criterion verification, hidden-gap discovery, architecture judgment, root-cause analysis, and other semantic review stay in the selected agent runtime.
FIX Legacy coworker profiles fail closed. The older generic profiles are documented as disabled defaults; source-code reading and voice-bearing content remain native to the selected agent model.
CI Security workflow shell-linting install is resilient to transient runner package-source failures. The linting jobs now use a preinstalled binary when available and disable broken vendor package sources before installing the distribution package, so external repository drift no longer blocks releases.

v2.50.2

July 6, 2026

FIX Installer bypasses token-reduction shims for compound file-search predicates. The Codex install path now resolves a real search binary before cleaning skill wrappers and listing bundled plugins, preventing shim failures when the runtime launches the installer with those shims already on the path.

v2.50.1

July 6, 2026

FIX Codex installer self-heals stale temporary probe hooks. The install path now replaces missing temporary probe commands in the runtime hook configuration with the canonical guard, preventing repeated hook-exit failures after the temporary directory is cleaned. Valid custom hooks are preserved.

v2.49.1

June 30, 2026

FIX Project scaffolding no longer seeds the retired backlog-archive.md. backlog-archive.md was abolished in v1.19.1 (completed/cancelled prose now lives in documentation/archive/{area|cancelled}/archive-{ID}.md and backlog.md carries only live items), but /dr-init first-time creation and the project-init scaffold tree still created the file from a template — so a freshly scaffolded project was born with a file /dr-doctor --fix immediately migrated away. The create-step, the scaffold-tree visuals (project-init skill + getting-started docs), and the help-command backlog description are corrected, the backlog-archive-template.md is deleted, and a bats regression guards the scaffolding surface against re-seeding the abolished file.

v2.49.0

June 29, 2026

CHANGE BREAKING (canon): the documentation root is renamed docs/ → documentation/. The framework’s 19 root docs were moved into the four Diátaxis categories (tutorials/, how-to/, reference/, explanation/), with archive/, evolution/, release-audit/, and ephemeral/ reserved as sibling directories (a Diátaxis category may not take those names). History is preserved via git mv. documentation/ is now the single canonical documentation root ecosystem-wide — the diataxis-docs mandate, the /dr-init scaffold, the Documentation Taxonomy Mandate, and the /dr-optimize drift detector all target it.
CHANGE Hard-flip compatibility — with a fix path, not just a reproach. The drift detector now treats a repo still on legacy docs/ as drift. A consumer repo is not left stranded: /dr-doctor gains an opt-in, idempotent, rollback-safe self-heal pass that performs the same git mv + Diátaxis split + reference rewrite, detecting legacy / partial / already-migrated layouts and restoring the original tree if any post-migration check fails.

v2.47.3

June 28, 2026

FIX Publishing rules reach content tasks earlier and at the gate. The fixed publish order, the FB/LinkedIn/VK two-link first comment, the article back-link closing gate, and the amplitude-strip video standard are now also surfaced in the pre-publish checklist (the hard gate run before every publish) and in the writer agent (so deliverables are planned for the order from the drafting stage), not only in the skill body. Closes a discoverability gap where the order rule lived only in the skill body and the publish command.

v2.47.2

June 28, 2026

FEAT Social-post video gains a bottom audio-amplitude strip. The animated-cover video generator now overlays a live narration-amplitude strip (a gradient oscilloscope, gold→crimson, pinned to the bottom edge) on top of the cover animation when narration audio is present. It is an addition on top of the cover cycle — not a bare full-frame waveform video, which stays forbidden as the whole post. On by default, tunable height and colours, and skipped automatically on cover-only clips.

v2.47.1

June 26, 2026

FIX Fixed social publishing order — Telegram → X → Facebook / LinkedIn / VK. The publishing skill and the publish command now treat the platform order as a hard contract rather than a reach heuristic: site → Telegram (canonical) → X (premium full-article) → Facebook / LinkedIn / VK. X is published before Facebook / LinkedIn / VK so its URL exists when their first comments are written — those comments must cross-link both the Telegram and the X post. The previous “Telegram, LinkedIn, Facebook, X, VK” ordering forced a back-fill pass to add the X link.
FIX Article social back-link block is now an explicit closing gate. A published article whose social posts exist but whose on-page social back-link block is missing or incomplete is treated as an incomplete publish — the publish task does not close until the block is present on every language version, points at the real permalinks, and is verified live.
FIX Manual browser publishing aligned to clipboard-only media. The manual-publishing guidance now mandates attaching media (image or video) via the OS clipboard, media first then text, and never the native file picker.

v2.47.0

June 24, 2026

FEAT Probe-before-emit ID-assignment invariant (<TASK-ID>). Task-ID selection in /dr-quick and /dr-init now uses a deterministic formula — max(claimed across archive ∪ tasks.md ∪ backlog.md) + 1 — probing all three claim surfaces before the ID is announced. The chosen ID is never emitted in reply text or any artefact until the probe completes.
FEAT Auto-bump on parallel-session race. When the computed candidate is already claimed by a concurrent session, both commands auto-bump to the next free ID and emit a warning — no operator prompt required. The existing three-way operator prompt for foreign-entry collisions is retained verbatim.
FEAT /dr-quick Stage Header re-sequenced. The header is now emitted after Step 2's probe completes (ID known), mirroring the /dr-init after-Step-4 pattern. The previous “first line of every response” wording that provoked premature emission is removed.
FEAT New dev-tools/next-free-id.sh helper. A pure-shell, shellcheck-clean helper implements the canonical ID-selection formula and auto-bump logic, making the behaviour empirically testable via bats. Absorbs <TASK-ID> (bats fixture with <TASK-ID> boundary test).

v2.46.0

June 23, 2026

FEAT Compliance gains a stale test-count classification rule. When a commit message claims N/N tests pass but a live re-run reports M/M with more tests, and those extra tests are verifiably present in the commit, the discrepancy is now classified as informational rather than a failure — the live count is recorded as authoritative and the run is not forced to re-commit. A normal polish-test addition no longer reads as a compliance breach.
FEAT New deterministic classifier-script template. A reusable Bash template for type-signal classifiers ships with the framework — message-file parsing with an input guard, a priority-ordered match helper, and a documented exit-code table — so projects that route messages by intent start from a tested skeleton instead of an ad-hoc script.
FEAT Verification-mode durability axis (carried from the prior cycle). Each acceptance wish can now declare whether its check is a one-off or a reproducible, committed artifact; a reproducible wish without a wired-in test or CI job is flagged (advisory during review, hard at compliance). The schema is additive and opt-in — existing checklists are unaffected.

v2.45.0

June 23, 2026

FEAT Orchestration autonomy policy is now a core capability, not a plugin. The autonomy policy data (the hard-gated safety floor and the action-to-policy map) and its loader moved from the opt-in orchestration plugin into the framework core, so the autonomous-execution command resolves its safety floor without enabling any plugin. With the policy stranded in a default-off plugin, the floor could silently collapse so that everything escalated; the floor now resolves from core and fails closed when its rules file is absent.
FEAT The orchestration slash-command resolves as core. Its registration no longer points at a plugin path, so the command is available out of the box. The transport runner (terminal multiplexer driver, inference-backend chain, bot/HTTP interface, audit backends) stays an opt-in plugin via thin shims that prefer the core policy loader and fall back to a one-cycle deprecation copy.
FIX Doc-only fast-path and deferral-prose path guard. The autonomous-execution command gained an L1 documentation-only fast-path, and the self-deferral prose scanner now tolerates spaces in the report path.

v2.44.0

June 22, 2026

FEAT Session resume command now carries a deterministic handle and a human-readable task label. The /dr-save resume block prints /dr-continue {SESSION-ID} as the copy-paste command — the session id selects exactly one saved session, so in a shared workspace with parallel agents a bare /dr-continue can no longer pick up another agent's session by modification time. Beside it, an annotation line shows ↳ {TASK-ID} — {title} (read from the active-task index, truncated and sanitised) plus a saved-time derived from the session id, so a human recognises which work they are resuming among many.
FEAT Multi-task sessions list only the other active task ids. When a save spans several tasks, the block names the recommended one in the annotation and lists the remaining ids on an Also active this session line — the current task is never duplicated, and the line is suppressed entirely for a single-task save.
FIX Snapshot-writer ergonomics. The stage-snapshot skill now states that --body-file is mandatory and that the wrapper's standard error must not be swallowed — the clear «missing required flag» message was being hidden by callers piping the wrapper through a truncating tail.

v2.42.0

June 20, 2026

FEAT Native spec-traceability layer (auto-layer, embedded in pipeline stages). A new read-only verification façade builds and validates the requirement graph wish_id → D-REQ → V-AC → plan-step → evidence across the artefacts a task already produces — no parallel specification tree, no external dependency, no second pipeline. Addressable D-REQ-NN identifiers and a Covers: D-REQ-* binding turn the previously advisory wish→criterion link into a machine-checkable graph. The /dr-spec standalone command was later retired (v2.43.0) — spec-traceability now runs automatically inside /dr-prd, /dr-plan, /dr-do, /dr-qa, and /dr-compliance via spec-graph-gate.sh, with no separate invocation needed.
FEAT Four pure-shell validators over one rule registry. dr-spec-lint.sh (core graph validator, named rules, --scope git-diff), dr-trace.sh (coverage buckets: covered / uncovered / dangling / orphaned / deferred), dr-lint.sh (umbrella façade with rule-registry introspection and a fail-closed mandatory-rule guard), and dr-spec-grade.sh (a computed projection only — never hand-edited, never affects routing). All share one contract: --format json, exit 0/1/2, and a mis-configured ruleset is a configuration error (exit 2), never a silent «0 violations».
FEAT Advisory-first rollout + /dr-verify integration. Activation order is dry-run → baseline → advisory window → hard gate for new/changed artefacts only; L1 skips the graph, L2 is advisory, L3+ becomes mandatory after a transition window. On --stage plan|all, /dr-verify's deterministic floor shells the graph validator and re-emits findings with source_layer: "floor" — reusing the existing severity and routing taxonomy, no new verdict enum.

v2.40.0

June 18, 2026

FEAT Post-relocate dead-IP sweep gate. A new fail-closed pre-archive gate (Step 0.35) fires when a task is a database relocation or decommission and blocks the archive while any live consumer still points at the retired database address. The gate is a read-only, network-free pair: dev-tools/check-db-relocation-class.sh arms only on a real relocation (a type: field or an explicit decommissioned_ip: frontmatter field, never on prose that merely describes the pattern), and dev-tools/dead-ip-consumer-sweep.sh scans local config surfaces, classifies hits as live or historical, and requires an audit document asserting zero live consumers. 25 bats tests.
FEAT Mesh-health pre-check for fleet sweeps. The infra-automation skill gains a pre-sweep reachability check: before a fleet sweep, ping each mesh address and log reachability plus the fallback strategy in the sweep log, rather than discovering an unreachable node mid-sweep.
CHANGE operational-resilience mandate: mandatory dead-IP sweep. The database-relocation runbook now requires the fleet-wide sweep as a mandatory pre-archive step, making the recurring stale-consumer failure class self-checking.

v2.38.0

June 15, 2026

FEAT Cross-runtime session handoff: /dr-save & /dr-continue. Two new commands capture and restore full session state across context resets and runtime switches (Claude Code → Codex CLI → Cursor). /dr-save writes a self-contained datarim/sessions/SESSION-{YYYYMMDD-HHMMSS}.session.md artefact with a 5-layer body (git state / active tasks / related files / open questions / failed approaches), 32 KB cap with non-truncatable L1/L5, append-only semantics, and T-8 secret redaction. /dr-continue reads the artefact in a clean window and strictly re-verifies every claim via live probes before resuming — emitting STALE SNAPSHOT, CLAIM-UNVERIFIED, and FILE-MISSING banners and routing to /dr-next or /dr-auto.
FEAT Claim-provenance enforcement. Every line in a session artefact containing pushed, merged, deployed, green, or passing must carry a verified: or assumed: tag. The writer script exits 1 on untagged claims; the validator exits 2. The consumer downgrades all verified: tags and re-elevates only those confirmed by live probe — eliminating the class of false-confidence restarts where a prior session marked work as done but the new session inherited a stale claim.
FEAT Squash-collision detection. /dr-continue detects the scenario where a parallel session squash-merged the agent's branch under a foreign commit header. It uses git merge-base --is-ancestor <sha> origin/main (not git cherry) and emits a CLAIM-UNVERIFIED banner with a content-landing diff so the operator does not falsely conclude work was lost.
FEAT New skills: session-handoff-writer and session-handoff-replay. Two new reference skills define the producer and consumer contracts. The bilingual replay renderer (ищи способ... / Find a way...) is factored as a shared section in skills/dr-next-snapshot-replay/SKILL.md § Shared Replay Renderer and cited by both /dr-continue and /dr-next.
FEAT Cursor command fanout. install.sh setup_cursor_runtime() now mirrors all commands/dr-*.md files into ~/.cursor/commands/ with dr- prefix, giving Cursor IDE first-class command access alongside Claude Code and Codex CLI.
FEAT Validator & squash-collision bats suite. A new dev-tools/check-session-handoff.sh validator (exit codes 0/1/2/3) and a dedicated tests/session-handoff-squash-collision.bats suite (7 tests using a full git fixture) pin the contracts. Total new bats coverage: 37 tests across writer, validator, and squash-collision suites.
CHANGE datarim/sessions/ added to .gitignore. Session artefacts are transient per-session state; not committed to the framework repo.

v2.37.0

June 14, 2026

FEAT Artifact Language Policy. The free-generated body of runtime artefacts (creative / PRD / plan / the analytical body of archive / reflection / compliance-report) now defaults to English, declared in a new CLAUDE.md § Artifact Language Policy adjacent to the English-Only shipped-surface section. The directive is auto-loaded into context at generation time; the coworker delegation path mirrors it via a new §12 in skills/coworker-context/SKILL.md.
FEAT Operator-configurable language override, no code. The default is overridable per project with a single documented line in the consumer’s own CLAUDE.md § Project-Specific Configuration (Artifact language: <lang>); a secondary DATARIM_ARTIFACT_LANG convention is documented for shell-aware coworker call sites. No new validator, no config file, no change to the closed init-task schema. Verbatim operator input, canonical operator-facing sections, and ordinary user-project content stay exempt.
FIX network-exposure gate no longer false-blocks init-task-only tasks. At early pipeline stages a task may have only an init-task artefact (no priority/type by schema); the tiered gate now resolves to skip (or advisory_warn when a network-diff signal is present) instead of fail-closing to hard_block. Fail-closed is preserved for genuinely malformed task descriptions. Three new regression tests pin the contract.

v2.36.0

June 14, 2026

FEAT /dr-auto surfaces the compliance outcome before the CTA. The commands/dr-auto.md terminal-cleanup step now prints one line stating how /dr-compliance resolved — the verdict (COMPLIANT / COMPLIANT_WITH_NOTES) when a compliance stage ran, or a skip-by-design reason at complexity levels whose routing has no compliance stage — immediately before the call-to-action block. Previously the operator saw only a bare archive CTA, which read as “compliance is never proposed”.

v2.34.0

June 14, 2026

FEAT Self-enforcing /dr-auto dispatch contract. The commands/dr-auto.md Step 5 re-assert sub-bullet is promoted from advisory “mechanics:” prose to a mandatory pre-dispatch MUST-gate. Before spawning any stage subagent the orchestrator MUST run auto-mode-marker.sh reassert as the first action of every per-stage dispatch. Skipping this step means skipping the dispatch gate.
FEAT Regression lint check-dr-auto-reassert-wiring.sh. A new deterministic shell lint scans commands/dr-auto.md Step 5 and exits 1 whenever the executable auto-mode-marker.sh reassert invocation regresses to prose-only (no adjacent mandatory cue). Registered in CI (.github/workflows/dev-tools-lint.yml) so the self-enforcement gate fires on every PR. Fence-exclusion logic ensures illustrative fenced blocks do not false-pass.
CHANGE New bats coverage. tests/check-dr-auto-reassert-wiring.bats adds 3 tests pinning the lint contract: passes on the wired spec, fails on a prose-only synthetic fixture, exits 2 on a usage error. Existing tests/dr-auto-marker-resilience.bats (6 tests) re-verified green.
CHANGE Visual-map drift fixes. Two stale entries in the navigation maps are corrected: command-dependencies.md is registered in the routing-invariants drift-mapping, and a /dr-compliance row is added to the panels-and-quality Quality Rules table.

v2.33.0

June 14, 2026

FEAT Auto-mode marker resilience. The datarim/.auto-mode-active marker now survives subagent dispatch. A new helper dev-tools/auto-mode-marker.sh (verbs: reassert / subagent-active) provides an idempotent re-assert mechanic: if the marker vanishes between Step 3 and a stage dispatch, it is rewritten before the next subagent is spawned. A bats regression suite locks the contract (5 tests: restore, idempotent, subagent-active without env-var, fail-safe, task-id mismatch).
CHANGE Relaxed activation contract for spawned subagents. The autonomous-mode skill (skills/autonomous-mode/SKILL.md) gains a "Spawned subagents (relaxed activation)" sub-rule. A subagent dispatched via the Agent tool does not inherit DATARIM_AUTO_MODE; it now activates the skill when its dispatch prompt carries an explicit auto-signal AND the re-asserted marker is present with a matching task ID. The top-level cycle still requires all three conditions.
CHANGE /dr-auto Step 5 wired for resilience. Two new sub-bullets in commands/dr-auto.md Step 5 document the mechanic: re-assert the marker at its current path before each dispatch, and carry the auto-signal in the subagent prompt. The helper path is referenced via MARKER_RELPATH so a future marker rename touches one constant, not every prose reference.

v2.32.0

June 14, 2026

SECURITY Public-surface de-personalisation. Personal names, handles, ecosystem hostnames, numeric GIDs, and Vault paths are removed from all shipped framework artefacts. A new CI gate scripts/personal-id-gate.sh scans the shipped surface against dev-tools/personal-id-forbidden.regex on every PR, blocking any artefact that carries operator-private data. Operator-specific configuration now lives exclusively in the gitignored ${DATARIM_LOCAL}/config/personal.env, loaded by a new generic cli/lib/load-local-config.sh (fail-soft, key-validated, no eval/source).
FEAT Personal config overlay (~/.claude/local/config/). install.sh now creates a config/ sub-directory inside the local overlay with a self-documenting README.md template. The generic loader reads personal.env from that path and exports valid keys into the shell environment — without executing any value. Four bats tests cover the injection-safety, bad-key, valid-key, and missing-file contracts.
FEAT Command-dependency graph. A machine-readable YAML source of truth (dev-tools/command-graph.yaml, 24 commands) records every command's stage, prerequisites, successors, and optional-at complexity levels. A derived Mermaid diagram (skills/visual-maps/command-dependencies.md) provides the human-readable and renderable view. Four bats tests validate YAML integrity, minimum command count, core-command presence, and diagram content.
CHANGE OG-1 resolved: /dr-help added to orchestrator rules. The single outlier in plugins/dr-orchestrate/rules/default.yaml is closed — /dr-help is now a resolvable pattern (confidence 0.95), aligning the classifier with the soak corpus, three existing surfaces, and the contract test. All 8 rules-loader tests pass.
SECURITY Security Mandate extended with S3.1. A new sub-rule in CLAUDE.md § Security Mandate and skills/security-baseline/SKILL.md § S3.1 codifies the no-personal-data policy for shipped artefacts, references the gate and loader, and defines the inline exemption fence ().

v2.31.0

June 10, 2026

FEAT Anti-deferral gate. A deterministic three-layer gate stops an agent from labelling its own unfinished work «out of scope / informational / not a blocker / I’ll fix later» and still passing QA, compliance, and archive. A new scanner dev-tools/check-deferral-prose.sh reads a QA or compliance report for deferral-tell phrases and cross-checks each against the set of files the task actually touched (git merge-base HEAD origin/main..HEAD); a deferral phrase about a touched file, with no verifiable follow-up or blocked_by artefact, blocks. Prose is not trusted — the touched-file set is the ownership boundary. Quoted phrases inside fenced code blocks or blockquotes are excluded so an honest report about the gate does not false-block, and a repeatable --extra-repo flag extends the scope for dual-repo framework tasks.
FEAT Override-authorship check. The expectations validator gains override_by / override_class / override_artifact fields. An agent can no longer self-certify a partial / missed wish with prose alone: an agent-authored override now requires an allowed class (time-dependent / external-blocker / operator-authorized / plan-scope-boundary) plus an artefact id that exists in the backlog or task index. Operator-authored overrides are accepted unconditionally.
CHANGE Gate wiring + operating rule FB-5a. /dr-qa Layer 3b runs the deferral scan as an advisory; /dr-compliance Step 5c runs it as a hard gate (a finding is NON-COMPLIANT); /dr-archive gains Step 0.45, placed before reflection so the follow-up heuristic cannot launder a self-inflicted loose end into a backlog item. A new operating rule FB-5a requires the agent to complete reversible authorised work itself (e.g. an authorised git push) rather than hand it back. Legitimate deferral is reserved for time-dependent or hard-external-blocked work, and only with a traceable artefact.

v2.30.0

June 6, 2026

FEAT Prod-readiness gate for deploy-class tasks. A new two-stage blocking gate verifies that the production runner is symmetric to the test runner before the pipeline recommends a merge, and again before a task can be archived. /dr-qa gains Layer 4g (a read-only test↔prod probe of sudoers, PATH, ports, systemd units, and runtime versions) and /dr-archive gains Step 0.4 (archive is blocked until the production merge is done and verified). The gate arms only for deploy-class work — tasks touching systemd units, sudoers, CI cutover jobs, or .env-deploy templates — detected by a new classifier dev-tools/check-deploy-class.sh. Production stays hard-gated: the probe is strictly read-only and predicts impact; any mutation is an explicit operator action. Closes the failure class where a change verified a hundred times on the test runner falls over on the first production command.
FEAT New skill: prod-readiness-probe. Defines what the gate checks and how it reports, with a four-verdict vocabulary (SKIP / PASS / FAIL / BLOCKED; BLOCKED never auto-resolves to PASS on an unreachable host). Hybrid execution: a project may author an optional datarim/deploy-readiness.yml contract (validated by dev-tools/check-deploy-readiness.sh) for a deterministic probe, or the probe falls back to an agent-driven checklist. The framework core stays stack-agnostic; project-specific runner data lives only in the optional contract.
CHANGE Self-evolution gains an anti-self-suppression rule. A reflection lesson that recurs — matching a prior reflection or describing a repeat of a known failure — can no longer be declined as «redundant with existing contract» and demoted to a memory note. A new evolution category promote-recurring-incident-to-gate turns such a recurring, advisory lesson into an enforced gate. The rule fires only on demonstrated recurrence, with cited evidence; genuinely novel lessons may still be declined.

v2.29.0

June 6, 2026

FEAT New /dr-quick fast-lane. A lightweight command for trivial fixes or quick lookups that skips the heavy init → prd → plan pipeline. It assigns a QCK-XXXX task id (new universal area-prefix, archived under quick/), runs a fast context scan on the runtime’s cheapest reasoning tier to locate where the change belongs, applies the fix, and writes a short archive entry — no PRD, plan, QA, or compliance. For one-file edits where waiting for full analysis is pure overhead.
FEAT Reflection moves to /dr-compliance. Reflection (lessons-learned + evolution proposals) now runs at a passing /dr-compliance verdict and stamps the reflection with a reflection_basis marker derived from the compliance report. /dr-archive Step 0.5 becomes a freshness gate: it re-runs reflection only when the file is absent, the marker is absent, or the marker is stale versus the current compliance report — otherwise it reuses the existing reflection. The mandatory-reflection guarantee is preserved: a task archived without a prior compliance pass still force-generates.
CHANGE /dr-auto is now a subagent orchestrator. Instead of chaining slash commands, /dr-auto spawns the matching agent per stage (planner / architect / developer / reviewer / compliance), summarises each result, and routes to the next stage. It drives a task to a passing /dr-compliance + reflection and stops there — archival stays an explicit operator step. Re-entering an already-completed stage after a review finding is first-class (the artefact is updated, not recreated).
CHANGE Command hygiene. The deprecated /dr-continue alias (and the dr-continue-snapshot-replay skill alias) were removed — one canonical name per concept (/dr-next and dr-next-snapshot-replay). Live inventory is now 24 commands and 54 skills.

v2.28.0

June 1, 2026

FEAT Tag-driven release environment provisioning. A new dev-tools/provision-release-env.sh sets up a GitHub deployment environment for a tag-driven publish (on: push: tags: [v*]). GitHub creates environments with a default policy that matches protected branches and silently excludes tags, so the first tag-driven publish of a brand-new package is rejected. The provisioner sets custom_branch_policies=true plus a {name: v*, type: tag} deployment-branch-policy, and preserves required reviewers on the manual-approval environment.
FEAT Dry-run by default. The provisioner only prints the planned GitHub API calls unless --apply is passed, mirroring the fail-closed posture of the rest of the release rails. It is idempotent: re-running skips a tag policy that is already present. The GitHub API edge is injected for deterministic testing (13 new regression cases).
CHANGE Release docs. A new how-to walks through provisioning (script quick-path, reviewer-id resolution, manual API equivalent, verification commands). The PyPI first-publish how-to and the release-process playbook now cross-reference it as a one-time prerequisite before the first publish.

v2.27.0

May 30, 2026

FEAT Anti-deferral gate. A new deterministic gate stops an agent from labelling its own unfinished work «out of scope / informational / not a blocker / I’ll fix later» and archiving anyway. New dev-tools/check-deferral-prose.sh scans QA and compliance reports for deferral-tell phrases and cross-checks each against the touched-file set (git merge-base..HEAD): a deferral phrase about a file the agent itself touched, with no verifiable follow-up / blocked_by artefact, is a hard block. A phrase about a genuinely foreign area, or one backed by a real follow-up ID that exists in the backlog, passes — keeping the false-positive rate low.
FEAT Override authorship. check-expectations-checklist.sh gains override_by / override_class / override_artifact. A partial/missed wish can no longer be waved through by an agent writing its own free-text override (the self-certification loophole): an agent override now needs an allowed deferral class plus a follow-up / blocked_by ID that exists in the knowledge base. Operator-authored overrides are accepted unconditionally.
FEAT Archive Step 0.4 + FB-5a. /dr-archive gains a mandatory Step 0.4 that re-validates expectations and re-runs the deferral scan before reflection — so reflection’s follow-up heuristic cannot launder a self-inflicted loose end into a backlog item ahead of the gate. /dr-qa runs the scan as an advisory; /dr-compliance runs it as a hard NON-COMPLIANT gate. A new operating rule FB-5a codifies the principle: complete reversible authorized work yourself, do not hand it back; defer only when time-dependent or hard-external-blocked, and only with a traceable artefact.
NOTES A legitimate deferral — results that need a 1+ day soak, or a hard external blocker — still clears every gate by citing a follow-up ID or blocked_by reference that exists in the KB. Scanners are fail-open on their own git-probe failure: an infrastructure hiccup never blocks an otherwise-clean archive. Four new regression suites cover the scanner, the override-authorship logic, the archive Step 0.4 surfaces, and the compliance gate.
CHANGE Repo↔site content parity. The framework README gained the naming-origin (the Latin datarium/dator root — «a store that gives»), a Website badge and reverse link to datarim.club, and a corrected component count (55 skills). The About page and bilingual content were realigned to the canonical 18 agents / 24 commands / 55 skills, and the repo VERSION was brought up to 2.27.0 to match the site. Pilot of the ecosystem repo↔site sync discipline; the drift detector reports the datarim product clean.

v2.26.0

Previous May 29, 2026

FEAT KB data-loss resilience. Every overwrite of a critical knowledge-base file (backlog.md, backlog-archive.md, tasks.md, activeContext.md, progress.md) now triggers a fail-soft pre-overwrite backup to datarim/.backups/<file>.<timestamp>.bak (FIFO rotation, default 10). Enforced at the PreToolUse hook so it catches both the Write tool and awk/tee/> redirect overwrites — the exact incident class that once zeroed a live backlog. Backups are git- and sync-ignored host-local recovery ground-truth.
FEAT Unified path resolver. A single canonical resolve-datarim-root.sh replaces three divergent walk-up re-implementations. --root now means the repo-root everywhere (the doctor previously meant the datarim/ dir — the mismatch silently suppressed the docs→history migration through the pipeline). A nesting guard rejects an already-nested root, eliminating the datarim/datarim/ directory class. A one-release shim normalises the legacy datarim-dir argument and warns.
FEAT Recovery how-to. New docs/how-to/recover-datarim-files.md documents the per-file source-of-truth priority chain (backup → sync-conflict → task artefacts → archive frontmatter → transcripts) and the datarim-doctor --fix repair recipe.
CHANGE Consumer-KB log storage retired the misleading datarim/docs/ directory. Append-only ledgers now live in the honestly-named datarim/history/, committed to git via a .gitignore negation block. datarim-doctor.sh --fix (or --scope=history) migrates the ledgers, relocates any ADR to documentation/architecture/, rewrites the consumer .gitignore, and removes the empty docs/ — idempotently and losslessly. Auto-heals on /dr-init.
NOTES The framework source-tree code/datarim/docs/ is unchanged — only consumer knowledge bases migrate. Six new regression suites cover the resolver, backup primitive, nesting guard, doctor --root contract, hook backup, and the migration. Bash-redirect backup detection is best-effort (literal targets); obfuscated redirects are out of scope.

v2.23.0

Previous May 28, 2026

FEAT Canonical Runtime Support Matrix. New § Runtime support in docs/use-cases.md documents the three supported runtimes with a 5-column matrix (Runtime / Install command / Hook integration / Bulk-read economy via RTK / Status). Claude Code stays primary; Codex CLI achieves parity through the coworker rtk shim; Cursor reaches parity through its native beforeShellExecution hook (rtk hook cursor in ~/.cursor/hooks.json). The earlier «no native hook / inherits via shared settings.json» framing was inaccurate and is replaced across all shipped surfaces. README.md, CLAUDE.md, docs/getting-started.md, and the Coworker README all link back to the canonical matrix as single source of truth.
FEAT RTK realities documented. templates/coworker-delegation-fragment.md § RTK plugin (opt-in) gains a paragraph on out-of-box rtk pitfalls — measured impact on macOS (git status +108%, git log --oneline -50 +6924%, lost git push completion marker on some repos) per upstream issue rtk-ai/rtk#2121 — and contrasts the raw binary with the coworker rtk plugin, which guards 13 signal-bearing git/gh commands via a default passthrough allowlist while still applying bulk-read economy to log dumps and file content reads. Multi-runtime parity preserved via the bundled Codex CLI shim.
CHANGE Skill / command counts corrected. CLAUDE.md and README.md updated from stale «45 skills, 23 commands core + 1 plugin» to live inventory «55 skills, 11 with supporting fragment directories; 24 commands core + 1 plugin». Drift accumulated across the <TASK-ID> universal skill-layout migration through v2.22.0.
The data catalogues on this site (data/skills/, data/commands/, data/agents/) are also fully resynced to the live inventory under the same release.
CHANGE Multi-agent narrative honest. docs/getting-started.md § Choose your runtime rewritten to enumerate Claude Code / Codex CLI / Cursor with full 3-runtime RTK parity (Cursor via its native beforeShellExecution hook) and explicit guidance on picking a runtime. install.sh --with-cursor now appears in the install command block alongside --with-claude and --with-codex.
NOTES CHANGELOG.md gained both the v2.23.0 entry and a retroactive v2.22.0 entry (the latter was missed at v2.22.0 release time even though VERSION had been bumped). Verification: grep -c '2\.22\.0' CLAUDE.md README.md VERSION → 0 hits in any shipped file; scripts/check-doc-refs.sh --root . zero delta vs pre-task baseline.

v2.22.0

Previous May 26, 2026

FEAT Outsider-friendly English instruction surface (<TASK-ID> epic: <TASK-ID> Wave 1 + <TASK-ID> Wave 2 + <TASK-ID> Wave 3). 164 files of shipped instruction surface (commands/ + skills/ + agents/ + framework root + plugin tree) rewritten from Russian-heavy jargon-dense prose to outsider-friendly English with first-use gloss for every framework term-of-art. The shipped surface now reads end-to-end for a developer who has never seen Datarim.
FEAT New validator: check-jargon-gloss.sh (V-AC-5). POSIX bash validator + manifest dev-tools/data/jargon-bank.txt (10 canonical terms — FB-1..8, Question Suppression Ladder, L1 Inline Resolution Rule, autonomous-ops, V-AC, AAL, Diátaxis, Class A/B gate, hard-gated, fail-soft). Enforces inline gloss or one-click link on first use per file. 7 bats cases, shellcheck clean.
CHANGE /dr-archive body-english gate: advisory → fail-hard. Step 0.5(e) now blocks archive with non-zero exit when Cyrillic appears in commands/ / skills/ / agents/ / plugins/ without an explicit allowlist marker ( per line or block-scope). Allowlist markers reserved for cases where the skill's meaning literally requires the foreign-language string (content-work skills, canonical schema names cited verbatim).
FEAT English-Only Shipped Instruction Surface mandate. Canonical text encoded in four CLAUDE.md surfaces (global, Arcanada ecosystem, Datarim project root, framework code/datarim/CLAUDE.md). Operator clarification «инструкции не могут содержать русские слова, если это не требует смысл скила» now lives as canonical rule, not just a feedback-memory note.
FEAT init-task Q&A round-trip: third disposition process-rule-artefact (<TASK-ID>). dev-tools/append-init-task-qa.sh --decided-by process-rule-artefact captures mid-task operator clarifications that produce persisted rule documents (memory + CLAUDE.md additions) as first-class append-log entries. New Process-rule artefacts: sub-heading replaces the standard rationale block. Validation: rationale must contain at least one path-like token. 6 bats cases green, backwards compatible with operator and agent dispositions.
FEAT V-AC axis-split skill — Pattern 2: gate-activation axis dry-run. skills/v-ac-axis-split/SKILL.md grows a second pattern: validator-activation tasks must dry-run-size their gate --scope during /dr-plan Component Breakdown. PRD Out-of-Scope deferrals under the same scope are self-blocking at /dr-archive time and must be resolved as either in-task rewrite or documented --scope reduction.
NOTES Test coverage: 22 bats cases for body-english + jargon-gloss validators (15+7), 6 for the new Q&A disposition. shellcheck clean on new and modified scripts. check-body-english.sh --scope commands,skills,agents,plugins PASS over 162 files; check-jargon-gloss.sh PASS over 162 files.

v2.20.0

Previous May 24, 2026

FEAT dr-orchestrate own bash HTTP server (<TASK-ID>). Replaces adnanh/webhook with a pure-bash HTTP/1.1 server on 127.0.0.1:31415 (socat fork-per-conn). New scripts/dr_orchestrate_router.sh parses HTTP/1.1 request from stdin and dispatches to handler scripts via 4-arg uniform signature <method> <path> <body-file> <headers-file>. New scripts/dr_orchestrate_server.sh wraps socat with pre-flight port-collision probe and --check / --once subcommands. Tier 1 loopback exposure; net listener delta vs 8090 baseline = 0.
FEAT /hooks/tmux 5-op dispatcher. scripts/tmux_dispatcher.sh handles op=list|attach|new|kill|read on POST /hooks/tmux + async polling on GET /hooks/tmux/job/<uuid>. Backed by Redis job store (scripts/redis_job_store.sh, fail-soft on connect-refused). Defence-in-depth: whitelist full-match for cmd, pane regex ^%[0-9]+$, UUID v4 strict format on path-segment — all rejections fire BEFORE any tmux subprocess invocation (audit-sentinel verified).
FEAT tmux_manager.sh extension. Added list / attach / new per V-AC-2 + tmux_*_safe wrappers (probe command -v tmux; consumer fail-soft on environments without tmux).
CHANGE orchestrator-input-handler.sh dual-mode migration. Mode-detection shim: $1 starts with - → legacy named-arg, [A-Z]* → uniform 4-arg, else → legacy positional. Uniform mode emits handler-protocol envelope (<status>\r\n<headers>\r\n\r\n<body>) matching the router contract. Legacy 26 Phase 4 CLI bats stay green; sync-shortcut 6/6 green. Hooks.yaml deleted.
CHANGE CLI dual-mode toggle. 5 cli/tests/tmux-*.bats gain DATARIM_CLI_USE_REAL_DISPATCHER=1 env switch. Mock mode (default) preserves Phase 4 26/26 green; real mode skips fixture-bound assertions (Phase G PROD smoke covers).
NOTES Test coverage: 40 new bats cases (15 HTTP server contract + 12 tmux endpoint + 8 path-traversal + 5 redis store + 5 migration). Full plugin suite 147/147 green recursive; CLI bats 26/26 both modes. shellcheck -S warning clean on all new + modified scripts.

v2.18.0

Previous May 23, 2026

FEAT Datarim CLI Phase 3 — HTTP client + slash-dispatch + AAL 3 mitigation scaffolding (<TASK-ID>). Ships code/datarim/cli/ top-level tree: datarim dispatch binary, lib/ modules (http.sh sync/async, audit.sh portable flock via python3 fcntl, notify.sh pluggable backends, kill-switch.sh, agent-id.sh UUID v7, accepted-risk-check.sh with 1h cache, uuid7-gen.sh 3-step fallback chain), subcommands/ (run, audit), standalone install.sh + bilingual RU+EN install-warning.sh. External agents (Codex / Cursor / custom) can now drive the full /dr-* pipeline through HTTP webhook to /dr-orchestrate v2.5.0; AAL 3 opt-in via new accepted-risk-aal.yml entry tune-0268-aal3-cli (expires 2026-08-21).
FEAT 6 AAL 3 mitigations. Dual-channel notifier with greater-than-or-equal-1-success fail-closed contract (exit 18) reusing @ArcanadaAssistantBot; JSONL audit log schema_version 1 with 10 required keys and 90d retention; kill-switch sentinel ~/.config/datarim-cli/HALT with no-bypass first-line check (exit 17); accepted-risk-aal.yml invocation-time gate (exit 23) + 7-day pre-expiry stderr warning; 6 RU + 6 EN canonical install warning lines; UUID v7 agent identity ($DATARIM_CLI_AGENT_ID) with timestamp window validation (exit 22).
FEAT New validators. dev-tools/check-cli-audit-schema.sh validates JSONL schema (10 keys, enums) and drives retention purge. dev-tools/check-accepted-risk-aal.sh validates the orthogonal AAL register (separate from CVE-only templates/accepted-risk.yml), enforces expiry, emits 7-day warning.
CHANGE Sync/async classification is CLI-local. cli/lib/slash-classification.yaml mirrors the OpenAPI canonical sync whitelist (dr-status, dr-help); non-idempotent commands refuse the sync path with exit 26. The PRD draft said parsed from fb-rules.yaml hard_gated_actions — fixture capture surfaced those are action.kind tokens, not slash-command names; plan D-B corrected to CLI-local table.
NOTES 57/57 bats green across 7 test files (V-AC-4..6, V-AC-19..28). Gap discovered during /dr-do: macOS lacks flock(1); resolved via portable python3 fcntl.flock wrapper. Standalone cli/install.sh — framework install.sh stays untouched so consumers without AAL 3 acceptance are not auto-exposed (plan D-C). New top-level code/datarim/cli/ directory; code/datarim/accepted-risk-aal.yml at repo root.

v2.17.1

Previous May 23, 2026

FIX Template path convention canon-correction. v2.16.1 standardised on bare $HOME/.claude/templates/<name>, which silently works only for the default symlink install. v2.16.2 migrates the canon to ${DATARIM_RUNTIME:-$HOME/.claude}/templates/<name> — the env-var form transparently supports the default symlink install AND non-default installs (./install.sh --project DIR, --copy with custom CLAUDE_DIR, plugin overlays) by reading the install location from $DATARIM_RUNTIME and falling back to $HOME/.claude/. 41 references across commands/*.md + skills/**/*.md + agents/*.md migrated in one pass.
CHANGE CLAUDE.md § Critical Rules #4 corollary rewritten. Recommended primary form is now the env-var fallback pattern; explicit $HOME/.claude/templates/X is documented as install-specific and discouraged for runtime markdown that consumer agents copy literally. datarim/templates/X still reserved for project-local overlay refs. Detector + bats unchanged (already accept all three prefix forms; 11/11 green).
NOTES Root motivation: operator review of v2.16.1 surfaced the install-topology blind spot — $HOME/.claude/templates/X resolves to the default install location only, missing project-local installs entirely. The env-var fallback pattern was already in canonical use for dev-tools/*.sh probes (see commands/dr-init.md:104,118 + docs/evolution-log.md:1694); v2.16.2 extends the same pattern to template refs. Closed in-cycle (no FU subtask).

v2.17.1

Previous May 23, 2026

FEAT Mandatory per-goal verification — schema v2 + evidence_type per wish. tasks/{ID}-expectations.md теперь обязателен для всех уровней L1-L4 (раньше — soft-window для L1-L2); создаётся прямо на /dr-init Step 4.7 (раньше — на /dr-prd или /dr-plan); каждый wish обязан нести evidence_type: empirical|static|measurement. Валидатор dev-tools/check-expectations-checklist.sh отвергает v2-файлы без поля + принимает v1 как legacy с DEPRECATION stderr (12-month sunset до 2027-05-23).
FEAT Per-wish detailed QA report. /dr-qa Layer 3b теперь пишет per-wish расширенный блок в qa-report-{ID}.md с 4 sub-headings («Evidence type», «Что было сделано для проверки», «Команда + результат», «Verdict»). empirical требует runtime command + output; measurement — numeric value + comparison; static допускает grep/file-check. Контракт: каждая цель оператора получает отдельный отчётный блок 1-к-1 mapping, как просил оператор: «по каждому пункту отчёт о том что было сделано для тестирования и какой получен результат».
FEAT Validator advisory warn-all-static + legacy pivot. scan_all_tasks --all emits WARNING когда все wishes имеют evidence_type: static (для L1 single-wish skeleton — exemption). Legacy tasks (legacy: true в task-description ИЛИ captured_at < pivot date = 2026-05-23, env-overridable через DATARIM_TUNE_0266_PIVOT_DATE) автоматически пропускаются. Severity advisory (exit 0); /dr-compliance может upgrade к BLOCKED.
CHANGE /dr-init Step 4.7 «WRITE EXPECTATIONS SKELETON». LLM-driven wish extraction из operator brief; L1 — 1-wish skeleton, L2-L4 — 2-5 wishes; fallback skeleton при vague brief; validator probe fail-soft; skip-if-exists. /dr-prd Step 5.5b + /dr-plan Step 5b понижены до «append-merge expectations checklist» (PRD/plan-driven дополнения только).
CHANGE Schema v1 → v2 migration. schema_version: 2 с обязательным evidence_type per wish; awk parser в валидаторе ветвится по schema; v1 принимается как legacy с DEPRECATION stderr; schema_version: 99 и неизвестные — exit 1. Шаблон templates/expectations-template.md обновлён под v2.
NOTES 42 новых bats-кейсов (Phase 1: 6 schema-v2 + Phase 2: 16 init Step 4.7 + Phase 3: 14 qa per-wish + Phase 4: 6 validator warn-all-static). Совокупно — tests/test-tune-0266-*.bats. shellcheck clean на расширенном валидаторе. Self-verification: задача первой проходит через свой собственный контракт (dogfooding — /dr-qa emit per-wish blocks для каждого из 8 wishes). Operator goal: «изначально, на стадии /dr-init, фиксировать условия поставленных целей задачи; на /dr-qa проверять каждый пункт детально и писать отчёт о тестировании по каждому пункту».

v2.16.1

Previous May 23, 2026

FIX Template path convention enforced in runtime markdown. 26 bare templates/<name>.<ext> references across commands/*.md and skills/**/*.md were absolute-qualified to $HOME/.claude/templates/<name>.<ext>. Bare relative refs resolved against the agent's cwd in consumer projects, breaking LLM-copied invocations such as coworker write --context templates/task-template.md with [Errno 2] No such file or directory. Root case: commands/dr-init.md § Reusable Templates bullet for task-template.md; 25 sibling hits surfaced by grep audit (same defect class, fixed in one pass per FB-4).
FEAT New detector dev-tools/check-template-path-convention.sh. Pure-bash + awk validator, locale-safe (LC_ALL=C), fence-aware (skips ``` ``` ``` blocks), markdown-link-aware (skips [`text`](../templates/X) renderer-side relative hrefs). Accepts $HOME/.claude/templates/, ${DATARIM_RUNTIME:-...}/templates/, and datarim/templates/ (intentional project-local overlay) as valid prefixes. Single --check mode: exit 0 clean / 1 offences / 2 usage. Regression: tests/check-template-path-convention.bats (11 cases). Per Datarim § Validation Discipline (orthogonal concerns get orthogonal tools), the detector ships standalone — not folded into datarim-doctor.sh.
CHANGE code/datarim/CLAUDE.md § Critical Rules #4 corollary. The «No absolute paths» rule now carries an explicit corollary for template references: bare templates/X in runtime markdown is forbidden; agent-facing refs MUST be $HOME/.claude/templates/X (or the env-var fallback in shell contexts); datarim/templates/X is reserved for project-local overlay refs. Detector + bats cited inline.
NOTES Bug origin: foreign consumer project (cwd outside Arcanada workspace) — agent read dr-init.md § Reusable Templates, copied templates/task-template.md verbatim into a coworker write --context invocation, path resolved to non-existent cwd/datarim/templates/task-template.md. Single-file root case bloomed into 26-hit pattern via grep audit; same regex-class defect across .md / .yml / .sh / .template extensions and subdir forms. Coworker behaviour itself is correct (generic file reader, exit 2 on missing context). Out of scope: coworker source, hook-guard, site explanation prose in data/commands/dr-archive.php (human-reader discoverability, not LLM-actionable).

v2.16.0

Previous May 22, 2026

FEAT Empirical stage-probe harness. New dev-tools/datarim-stage-probe-init.sh / datarim-stage-probe-coworker-echo.sh / datarim-stage-probe-cleanup.sh + auto-detect journal hook in scripts/lib/snapshot-writer.sh. While /tmp/datarim-test-{ID}/ exists, every write_stage_snapshot call appends one journal line documenting whether the operator-visible response carried the Stage Header banner and CTA footer. Operator-facing how-to: docs/how-to/datarim-harness.md. Auto-detect by directory presence — zero cost when harness inactive, fail-soft per V-AC-7.
FIX Snapshot writer silent-fail under zsh-parent shells. scripts/lib/snapshot-writer.sh uses BASH_SOURCE[0] for sibling-script resolution; under zsh (default macOS user shell) the array is unset, the writer fails with command not found: write_stage_snapshot at exit 127, and no snapshot is written. Empirically detected in workspace: datarim/snapshots/ remained empty across multiple pipeline cycles. Fix: new dev-tools/snapshot-writer-wrapper.sh wrapper forces bash -c execution; skills/cta-format.md § Snapshot Emission recipe updated to use the wrapper.
FEAT Coworker context propagation. New skills/coworker-context.md — canonical Datarim conventions reference for external LLMs invoked via the datarim coworker profile. Stage Header, YAML byte-exact, append-log Q&A, expectations Option B, snapshot frontmatter, PRD ↔ archive mirror, Diátaxis, history-agnostic, Supreme Directive. ~/.config/coworker/profiles.yaml::datarim.system_prompt rewritten from 56 generic words to ~300 words carrying nine of ten mandate keywords explicit. External LLMs now receive convention instructions instead of generating plausible-but-non-compliant documents.
CHANGE Stage Snapshot Emission recipe shape. skills/cta-format.md § Snapshot Emission now invokes bash dev-tools/snapshot-writer-wrapper.sh instead of the previous direct source scripts/lib/snapshot-writer.sh && write_stage_snapshot pattern. Operator-visible warning string is also updated to mention the wrapper.
NOTES New regression test: tests/stage-probe-harness.bats (10 cases) — init / cleanup mode & regex & symlink, writer header/CTA detection in body, wrapper under bash. All 10 PASS locally. shellcheck -S warning clean on all four new scripts. scripts/stack-agnostic-gate.sh + scripts/task-id-gate.sh PASS on the new skill.

v2.14.0

Previous May 22, 2026

FEAT Business-facing archive and compliance report contract (<TASK-ID>). The archive and /dr-compliance report templates now answer the operator's question «что я просил и что вы сделали» in plain Russian, in four mandatory top-level sections in strict order — «Начальная задача», «Как решили», «Артефакты задачи», «Следующие шаги» — followed by an audit addendum under a --- horizontal rule that carries the technical surface (verification_outcome mirror, AC table, lessons learned, operator handoff, related).
FEAT «Как решили» bullet-list contract. Single-level bullet list. One bullet per item in the operator brief, in original order, with quoted item + Russian status word («выполнено» / «частично» / «не выполнено» / «неприменимо» — never the schema enum met/partial/missed/n-a) + one or two plain-language sentences. Expectations from tasks/{ID}-expectations.md fold into the same list with marker «(уточнение брифа)». The previous top-level ## Выполнение ожиданий оператора heading is retired.
FEAT New canonical templates/compliance-report-template.md. Mirror of the archive shape (four operator-facing top sections + audit addendum carrying the 7-step verdict table wrapped in , remaining risks, related links). Frontmatter: task_id, date, verdict (COMPLIANT / COMPLIANT_WITH_NOTES / NON-COMPLIANT), optional scope.
FEAT New dev-tools/check-banlist-on-prose.sh validator. Bash wrapper does argparse + path-traversal regex (^[A-Za-z0-9._/-]+\.md$). Awk one-shot skips YAML frontmatter (first --- block) and honours  +  fence markers; tokenises ASCII tokens of length ≥ 3, lowercases, looks up skills/human-summary/whitelist.txt then skills/human-summary/banlist.txt. Exit 0 clean / 1 offences (file:line:token) / 2 usage. shellcheck -S warning clean.
CHANGE Sync of commands/dr-archive.md Step 2, commands/dr-compliance.md Step 7, skills/compliance.md § Output, skills/human-summary.md § See also. The four-section + audit-addendum contract is the single source of truth across the command, the skill and the templates. The 7-step compliance verdict table is wrapped in  so English column headings bypass the banlist on the prose body. Existing archive documents under documentation/archive/ are grandfathered.
NOTES New: tests/tune-0255-archive-business-structure.bats (10 cases) + tests/tune-0255-compliance-template-shape.bats (4 cases). Retired: tests/tune-0210-archive-expectations-section.bats (T6–T10 ported into the <TASK-ID> suite, T1–T5 retired with the heading removal). Validator passes on both new templates. Regression bats (init-archive-structural-guards, archive-contract-lint) stay green. The pre-existing baseline task-id-gate + description-length + workflow-lint failures persist (not introduced by this release).

v2.13.0

Previous May 21, 2026

FEAT Per-task stage snapshots (<TASK-ID>). Every /dr-* command now persists its final operator-visible response (Summary + Gate Results + CTA) to datarim/snapshots/{TASK-ID}.snapshot.md with overwrite semantics, 8 KB hard cap, mkdir-based atomic lock and chmod 600. Producer side wired through a single touchpoint: skills/cta-format.md § Snapshot Emission — no per-command patches.
FEAT Snapshot-First context resume. /dr-next {TASK-ID} (formerly /dr-continue) Step 2.5 reads the snapshot before task-description / init-task / activeContext and emits a replay-prompt with the recommended CTA, a bilingual autonomy reminder (RU + EN), and a literal done before: body. /dr-orchestrate Snapshot-First Resume forwards recommended_next to subagent_resolver.sh as --hint. Missing or malformed snapshot → silent fallback to legacy behaviour.
FEAT Archive lifecycle. /dr-archive Step 0.95 moves the final snapshot from datarim/snapshots/ to documentation/archive/<subdir>/snapshots/{TASK-ID}-final-stage.md via the existing prefix_to_area() resolver — final stage stays grep-able in the long-term archive.
FEAT Two new skills + validator + how-to. skills/stage-snapshot-writer.md (producer contract) + skills/dr-next-snapshot-replay.md (formerly skills/dr-continue-snapshot-replay.md, consumer contract with ≥ 3 worked examples of the CTA-selection heuristic) + scripts/lib/snapshot-writer.sh + dev-tools/check-stage-snapshot-on-exit.sh + docs/how-to/stage-snapshots.md (Diátaxis how-to category bootstrapped). Kill switch: DATARIM_DISABLE_SNAPSHOT=1.
NOTES 44 new bats cases across 10 suites (exceeds the 22+ plan target): writer overwrite + size cap + frontmatter schema + shellcheck + flock race + cta-format integration + dr-continue / dr-orchestrate replay + cleanup-on-archive + prefix-to-subdir cross-check. cta-format.bats regression unchanged green. Stack-agnostic gate PASS; task-id gate PASS; shellcheck -S warning clean on both new shell artefacts.

v2.12.0

Previous May 18, 2026

CHORE Removed copy-mode helper scripts. The pair of advisory drift-detection / curation scripts (DEPRECATED since v1.17 when the symlink-default operating model landed) are removed from the framework. Under symlink mode runtime IS the repo by inode — git diff is the canonical drift surface, so no parallel guard remained meaningful. Copy-mode users keep the documented resync recipe: git pull && ./install.sh --copy --force --yes. Three regression bats files that pinned the deprecated scripts (~146 LoC of tests) removed alongside.
CHORE Documentation cleanup, six surfaces. docs/getting-started.md § Updating and § Drift-between-repo-and-runtime rewritten to drop the deprecated tooling; docs/symlinks.md § How install.sh detects support / Migration from copy mode / Verification reworded; README.md § Drift check renamed to § Verifying the install with ./validate.sh as the canonical command; skills/datarim-system.md § Loading order copy-mode paragraph; skills/utilities/recovery.md Step 5 recovery recipe; skills/testing/bats-and-spec-lint.md static-grep exemplar and «Exemplar» reference.
CHORE Updater simplified. update.sh drops the post-install verify step and the dry-run drift listing — symlink mode exits early after git pull (unchanged contract), copy mode runs install.sh --copy --force --yes only. Help text + step-list synchronised. install.sh INSTALL_SCOPES comment now anchors the scope contract to tests/install.bats T34/T35/T36 (the canonical guard).
NOTES Stack-agnostic gate PASS; task-id gate PASS; bats suite green minus the three removed files (baseline 640 → ~634 expected after deletion); scripts/datarim-doctor.sh --quiet exit unchanged (pre-existing legacy-schema findings on workspace operational files, not introduced here). Re-allocated mid-flight from stale <TASK-ID> backlog reservation to <TASK-ID> to preserve grep -E '<TASK-ID>' audit-trail unambiguity (the historical <TASK-ID> archive of 2026-04-29 covers the multi-agent workspace archive semantics, not script removal).

v2.11.0

Previous May 16, 2026

FEAT Agent autonomy restored on /dr-init and /dr-archive. Symmetric revert of the operator-only contract introduced in 2.10.0 per the FB-rules (Autonomous Agent Operating Rules) mandate. Removed the disable-model-invocation: true frontmatter flag, the 🔒 lock-emoji in command H1 and table rows, the Operator-only marker blockquotes (rewritten as neutral «Contract» blockquotes that name the in-code guards), the planner / compliance STOP-rule paragraphs, the cta-format § Operator-only commands section with its 🔒 badge convention, and the pipeline-routing Mermaid classDef operatorOnly styling on both lifecycle commands.
FEAT Structural guards stay enforced in code. The pre-archive-check.sh schema gate + staged-diff audit at /dr-archive Step 0.1, the datarim-doctor.sh --quiet probe at /dr-init Step 2.4, the blob-swap recipe for non-interactive shells, the prefix → archive-subdir routing, and the Operator Handoff section template in templates/archive-template.md are all unchanged. Relaxation touches only the discovery layer (Skill enumeration) and cosmetic surfaces — never the data-integrity protections.
FEAT Inverted regression bats. tests/operator-only-commands.bats renamed to tests/no-operator-only-on-init-archive.bats with all 13 assertions inverted from «marker present» to «marker absent». Preserves git-history signal that the contract once existed and fires red if it ever drifts back in. Continuity for CI artefact tracking (bats count stable).
FEAT New structural-guards regression bats. tests/init-archive-structural-guards.bats (9 invariants) locks the in-code guards listed above — pre-archive-check.sh ≥ 3 references in dr-archive.md, datarim-doctor.sh in dr-init.md, PRE-ARCHIVE CLEAN-GIT CHECK header, blob-swap recipe, Archive Area Mapping, Operator Handoff section reference, STRUCTURAL COMPLIANCE CHECK, WORKSPACE CROSS-TASK HYGIENE CHECK, and the Operator Handoff section template in archive-template.md.
NOTES Stack-agnostic gate PASS on touched files; task-id gate PASS; bats green (640/640 — baseline 631 + 9 new structural-guards invariants); scripts/datarim-doctor.sh --quiet exit 0. Supersedes <TASK-ID>. Single-commit reversible via git revert.

v2.10.0

May 15, 2026

FEAT Arcanada Ecosystem Security Policy Mandate. Datarim ships the contract surface for the new ecosystem-wide security policy: canonical 10-section SECURITY.md template (Reporting / Disclosure SLA / Supported Versions / CI Gate Floor / Accepted Risks / Hardening Baseline / Standards Mapping / Embargo Policy / Hall of Fame / Scope) with consumer placeholders {{REPO_NAME}} / {{STACK}} / {{SUPPORTED_VERSIONS_TABLE}}; machine-readable accepted-risk.yml schema v1 (advisory-id regex, severity / scope / reviewed_by enums, reason minimum length, re-review window capped at last_review plus ninety days).
FEAT Reusable security-audit workflow. .github/workflows/reusable-security-audit.yml exposes a workflow_call with four stack profiles — typescript_pnpm, rust_cargo, python, framework. First step is the SECURITY.md presence-gate; second step validates the consumer's accepted-risk register when present; third step dispatches the stack-specific dependency audit. Final sentinel audit complete exposed for downstream verification.
FEAT Stale-trigger watcher. .github/workflows/security-stale-trigger.yml runs cron '0 9 * * 1' (Monday 09:00 UTC) plus manual workflow_dispatch, walks the configured ecosystem repo list, fetches each consumer's accepted-risk.yml, and POSTs warning / fatal events to the existing Ops Bot endpoint when an entry's re_review date has passed. Severity escalates from warning to fatal after 30 days overdue; fail-soft on Ops Bot non-2xx and on missing secret.
FEAT New gate tool dev-tools/check-security-policy.sh. Two orthogonal modes per the yaml-policy-loader-orthogonality contract: --check verifies SECURITY.md at repo root (defaults --repo to current directory), --validate-yaml <FILE> enforces schema v1 on the accepted-risk register. Pure bash plus awk, zero runtime dependencies; macOS BSD date and GNU date both supported via probe-and-fallback.
FEAT Cross-link section in framework CLAUDE.md. Datarim ships the contract surface only; the canonical mandate text is consumer-canonical per the rank-1 mandate canonical-text split. Reference consumer link recorded; conflict resolution with Supreme Directive Law 1 (Non-Harm) takes precedence over re-publish urgency.
NOTES Stack-agnostic gate PASS; public-surface lint PASS on shipped artefacts; bats green (15 new cases on top of the existing baseline); actionlint and zizmor zero on the two new workflows; shellcheck zero on the gate tool. Caller fixtures for act --dryrun drive each of the four stack profiles to the audit complete sentinel.

v2.9.0

Previous May 14, 2026

FEAT Init-task Q&A auto-append. Every operator clarification round captured by a pipeline command now lands in tasks/{TASK-ID}-init-task.md § Append-log as a structured block — verbatim question, verbatim answer, one-line summary, and a Decided by: operator|agent marker. When the operator does not answer, the agent decides autonomously per the Autonomous Agent Operating Rules (FB-1..FB-5) and records a ≥ 50-character rationale in the same block. Six pipeline commands write the block via dev-tools/append-init-task-qa.sh at a new APPEND Q&A IF ANY step (/dr-prd, /dr-plan, /dr-design, /dr-do, /dr-qa, /dr-compliance). /dr-init and /dr-archive stay read-only by contract. Backwards-compatible: tasks without an init-task file are not blocked.
FEAT Extended skill init-task-persistence. New ## Q&A round-trip contract section defines the block format (five mandatory subheadings — Question, Answer, Decided by, Summary, Conflict with existing wish; sixth Decision rationale ≥ 50 chars when decided_by is agent), the operator|agent decision-author enum, conflict-routing rules (Conflict with existing wish → return task via /dr-do --focus-items <wish_id> or /dr-prd), and the legacy fallback for tasks without an init-task file.
FEAT New utility dev-tools/append-init-task-qa.sh. Atomic Q&A block append with mkdir-based per-task lock (macOS-portable, no flock assumption), temp-file + mv write, realpath boundary check (target MUST resolve inside datarim/tasks/), 100 KB per-file size cap (DATARIM_QA_MAX_INPUT_BYTES), and Security Mandate § S1 file-only free-form input contract (no operator text as literal CLI strings). Exit codes 0 / 1 / 2 (appended / IO / usage).
FEAT Extended validator dev-tools/check-init-task-presence.sh. New validate_qa_blocks awk pass detects ### <ISO> — Q&A by /dr-<stage> (round N) headings, asserts five mandatory subheadings, allowed Decided by enum, and ≥ 50-char Decision rationale body when Decided by: agent. Backwards-compatible: init-task files without Q&A blocks continue to pass.
FEAT /dr-qa Layer 3b gains a Q&A round-trip verification sub-section. Two checks: agent-decision implementation grep (every Decided by: agent block must be reflected in changed files / task description / archive draft — unreflected raises Layer 3b FAIL, operator-overridable) and Conflict closure verification (every Conflict with existing wish: <wish_id> block must have a matching closure entry — unclosed raises Layer 3b BLOCKED and routes the task back to /dr-do --focus-items <wish_id>). Both checks fail-soft when no Q&A blocks exist.
NOTES Stack-agnostic gate PASS; shellcheck zero on the new utility and the extended validator; bats green (18 new tune-0216-qa-roundtrip cases on top of the 570-case v2.8.0 baseline; legacy 13 init-task cases unchanged).

v2.8.0

May 14, 2026

FEAT Operator-memory pipeline upgrade. Seven related improvements ship under one umbrella: «remember what the operator asked for, across the full pipeline». Verbatim init-task persistence, operator wishlist with verification gate, browser-based frontend QA, plain-language operator recap across three commands, archive section that mirrors the wishlist outcome, refreshed visual maps, and a coherent docs/site fanout. Backwards-compatible for legacy tasks via a 30-day rolling soft window; new gates default to info-severity advisories that never block legacy pipelines.
FEAT Init-task persistence (F1). Every /dr-init writes a per-task init-task.md with closed-schema frontmatter and a verbatim ## Operator brief section. Every later pipeline command reads it at first step; divergences from operator intent land in the task-description Implementation Notes. New validator dev-tools/check-init-task-presence.sh with --task / --all modes and a 30-day rolling soft window (info < 30 d, warn ≥ 30 d, never blocker for legacy tasks). 13 bats cases.
FEAT Expectations checklist + verification gate (F2 + F3). /dr-prd (L3-L4) and /dr-plan (L2 without PRD) write an operator-readable wishlist in plain Russian — kebab-slug wish_id (cyrillic allowed), История статусов running log, Текущий статус enum, optional override line ≥ 10 chars. /dr-qa Layer 3b and /dr-compliance Step 5b verify the checklist; missed items without operator override route the task back to /dr-do --focus-items <wish_ids> via the FAIL-Routing CTA. New validator dev-tools/check-expectations-checklist.sh; cyrillic wish_ids round-trip through shell arguments safely. 16 + 8 bats cases.
FEAT Browser-based frontend QA (F4). When a task touches any frontend markup, /dr-qa Layer 4f resolves an available browser tool (CLI → MCP → env-browser → none), acquires a per-task lock, opens the local dev surface, and writes screenshot + trace + summary into datarim/qa/playwright-{TASK-ID}/run-<ISO-ts>/. Skipped silently for non-frontend tasks. Three headed modes: default headless, lenient --headed (no display ⇒ finding + fall through), strict --headed-strict (no display ⇒ exit 2). New detector dev-tools/detect-playwright-tooling.sh; mkdir-fallback lock; path-traversal guard. 15 bats cases.
FEAT Plain-language reports across all three operator-facing commands (F5, absorbs the standalone preview from v2.7.0). /dr-qa, /dr-compliance, and /dr-archive end with a four-sub-section recap («Что было сделано» / «Что получилось» / «Что не получилось / осталось открытым» / «Что дальше») between the technical block and the next-step block. Anglicism banlist (around 50 ASCII tokens) + universal-term whitelist (around 30 terms — JSON, OAuth, HTTP, CLI, RFC, CI/CD, …) + per-paragraph  escape hatch (≤ 2 fenced paragraphs per recap). Severity ladder: 1st offence ⇒ info, 3rd ⇒ warn, 5th ⇒ block. Archive documents written before this contract are grandfathered and never re-validated. 24 bats cases.
FEAT Archive expectations section (F6). Every archive document carries a new ## Выполнение ожиданий оператора section between Final Acceptance Criteria and Known Outstanding State / Operator Handoff. Each wish from the expectations checklist is rendered as a single-level bullet with the plain-language status word (выполнено / частично / не выполнено / неприменимо — never the raw schema enum) plus one or two sentences of comment sourced from the most recent История статусов reason. No tables; banlist applies; missing expectations file ⇒ explicit «Чек-лист ожиданий не заводился» line preserves the canonical archive shape. 10 bats cases.
FEAT Visual maps refreshed (F7). The fragment-index visual maps gain three new artefact nodes (init-task, expectations, playwright-run) in a new «Artifact Flow Across the Pipeline» Mermaid diagram, four new skill nodes (init-task-persistence, expectations-checklist, playwright-qa, human-summary) in the Agent ↔ Skill dependency graph, and Layer 3b + Layer 4f branches in the /dr-qa stage flow. 18 bats cases.
FEAT Skill count: 41 → 45. Four new operator-facing skills ship: init-task-persistence, expectations-checklist, playwright-qa, human-summary. All consumer surfaces (CLAUDE.md, README.md, docs/skills.md, public site) brought to the same count.
NOTES Stack-agnostic gate PASS; gate sweeps green; shellcheck zero on new shell tools; security gates green. Bats green (13 + 16 + 8 + 15 + 24 + 10 + 18 = 104 new cases, on top of 466 existing — 570 total, 565 passing with 5 pre-existing failures unrelated to this release).

v2.7.0

May 13, 2026

FEAT Topic-overlap advisory in /dr-init Step 2.5b. A non-blocking check compares the fresh task description against the pending backlog and surfaces any item that shares ≥2 keyword stems. RU + EN tokenisation, hand-curated stopwords, crude suffix stemmer — Python 3 stdlib only, no pip dependencies. Operator picks duplicate / refine-scope / orthogonal before committing to a new task ID. Exit 0 by contract — pipeline ordering unchanged.
FEAT dev-tools/check-topic-overlap.py — top-N significant stems against pending backlog titles; text (default) and json output formats; --include-status flag for pilots that need to scan in_progress items too.
FEAT dev-tools/data/stopwords-{en,ru}.txt — ≥200 entries per language, including Datarim domain noise.
FEAT commands/dr-init.md — Step 2.5b inserted after the workspace-hygiene check. Skips silently when python3 is absent, the backlog has no pending items, or the detector is missing on an older install.
FEAT tests/dr-init-topic-overlap.bats + ...-fp-budget.bats + ...-latency.bats — PRD cases a/b/c, FP rate <10%, TP rate ≥4/5, ≤300 ms on a 500-item synthetic backlog.
FEAT Human-readable operator summary at the end of /dr-compliance and /dr-archive. A new skill defines a 4-sub-section recap (what was done / what worked / what didn't work or is still open / what's next) that both operator-facing commands now emit between their technical block (verdict / archive write) and the CTA block. The recap follows the operator's most recent message language (Russian default for Arcanada consumers, English otherwise), bans tables and jargon, and is capped at 150–400 words. The technical output is unchanged.
FEAT skills/human-summary.md — contract: 4 fixed sub-headings, length budget 150–400 words, anti-patterns (tables, English loanwords in Russian text, bare task IDs, multi-level nested lists, acronyms without expansion, emoji, mixed-language summaries), RU and EN mini-examples.
FEAT commands/dr-compliance.md Step 8 — HUMAN SUMMARY. Runs on every verdict; on NON-COMPLIANT the «what didn't work» sub-section carries the failure detail in plain language and «what's next» mirrors the FAIL-Routing CTA without command syntax.
FEAT commands/dr-archive.md Step 8 — HUMAN SUMMARY. Sourced from the just-written archive document plus the reflection file. Chat-only — archive and reflection are not mutated.
FEAT tests/test-human-summary-contract.bats — 9 spec-regression tests guarding skill existence, four mandated sub-headings, RU+EN mini-examples, length budget declaration, and cross-references from both commands.
NOTES Stack-agnostic gate PASS; task-id gate PASS; bats green (topic-overlap 6/6 + human-summary 9/9).

v2.6.0

May 12, 2026

FEAT Autonomous Agent Operating Rules — new rank-1 ecosystem mandate spawned from <TASK-ID> Phase 4. Eight canonical rules (FB-1..FB-8) govern agent autonomy when operator briefs are incomplete, complex, or ambiguous. Conflict resolution: Supreme Directive Laws 1-5 > Autonomous Agent Operating Rules > AAL Mandate > project-specific mandates.
FEAT plugins/dr-orchestrate/rules/fb-rules.yaml — machine-readable policy block (8 rules with enforcement_layer / tier / default_action / reversibility_required / audit_required / conflicts_with_law) plus a hard_gated_actions: list (prod-deploy, secret-rotation, irreversible DB, public communication, finance, legal, force-push-main, git-history-delete, multi-user-visible action).
FEAT plugins/dr-orchestrate/scripts/rules_loader.sh — new load_fb_policy() and load_fb_hard_gates() entry points, orthogonal to the existing prompt-pattern load() stream (separate schema, separate consumers).
FEAT Framework CLAUDE.md § Autonomous Agent Operating Rules (cross-link) defines the contract surface; consumers mirror the canonical FB-rules text in their own ecosystem CLAUDE.md before enabling dr-orchestrate plugin.
DOCS Spawned 14-task ecosystem backlog under Source: PRD-<TASK-ID> across CONS / ARCA / MUN / LTM / SRCH / CONN / INFRA / SEC / AGENT / TUNE prefixes — Consilium production deploy, voice-reply escalation UX, dev-agent boundary, backlog import API, long-term memory layer, retrieval over reflections, structured-output for CLI agents, DEV-server tmux provisioning, Supreme-Directive safety review, council escalation endpoints, public-surface scan, AAL audit recap, mandate sync audit, consumer rollout tracker.
NOTES Stack-agnostic gate PASS; task-id gate PASS; shellcheck zero. Phase 4 ships the contract surface and ecosystem documentation; Phase 5 (first self-driving cycle on DEV) tracked separately under <TASK-ID> umbrella.

v2.5.0

May 12, 2026

FEAT /dr-orchestrate bot-interaction interface — OpenAPI 3.1 inbound contract (POST /orchestrator/input, Bearer auth, sync-shortcut whitelist dr-status/dr-help with X-Sync-Timeout ≤ 2000 ms, async 202 default).
FEAT Reference impl via adnanh/webhook v2.8.3 (Go single binary, MIT) + config/hooks.yaml trigger config + scripts/orchestrator-input-handler.sh shell adapter (atomic ULID-named file write into ~/.local/share/datarim-orchestrate/inbox/).
FEAT cmd_run.sh inbox-poll branch — dequeues oldest inbox JSON per cycle, injects .command as UNKNOWN_TEXT, falls through to the existing semantic-parser → resolver pipeline.
FEAT Outbound _emit_devbot emitter replaces the v0.2.x stub. Two backends: callback (default, HMAC-SHA256 sign via scripts/outbound-hmac-sign.sh with X-Timestamp + 300 s replay window) and redis (opt-in via DR_ORCH_OUTBOUND_BACKEND=redis, publishes to orchestrator-out:{session_id} via scripts/outbound-redis-publish.sh).
SECURITY Activation gated on DR_ORCH_ESCALATION_DEVBOT_URL env — unset ⇒ silent return 0 noop, never exit 99. Rollback = unset env, instant revert.
SECURITY Network exposure Tier 1 (loopback 127.0.0.1:8090). Bearer secret via Vault ref vault:secret/datarim/orchestrator/bearer; HMAC secret via Vault ref vault:secret/datarim/orchestrator/hmac_secret. Secrets never in argv or logs; _redact chain reused on bodies.
TEST 11 new bats suites (5 contract, 1 integration, 1 security, regression-clean against 68 pre-existing tests). Schemathesis contract suite + CI workflow (.github/workflows/dr-orchestrate-contract.yml) drives property-based fuzz against the live reference impl on an ephemeral port.
TEST dev-tools/check-agent0017-live.sh — manual pre-activation gate (curl /healthz + smoke POST /prompts) before operator sets DR_ORCH_ESCALATION_DEVBOT_URL in production.
DOCS Public-surface sync: plugins/dr-orchestrate/README.md, framework CLAUDE.md + README.md, data/commands/dr-orchestrate.php (Bot-Interaction Interface section, EN + RU), config.php version bump.
NOTES Plugin plugin.yaml bumped 0.2.1 → 0.3.0. Unblocks <TASK-ID> (user-config bot_interaction schema) and <TASK-ID> M3 (pipeline driver via this interface). Stack-agnostic gate PASS; task-id gate PASS; shellcheck/gitleaks zero.

v2.4.0

May 11, 2026

FEAT /dr-orchestrate Phase 2 — Subagent Inference Layer. On parser miss (confidence: 0), cmd_run.sh dispatches to subagent_resolver.sh, a multi-backend AI CLI chain (coworker-deepseek → claude --print → codex exec). Per-backend 15 s timeout, FD-3 close for bats-harness compatibility, missing-backend dedup via state-dir sentinel, lenient JSON extraction (raw / fenced / prose-wrapped). Caller (cmd_run.sh) gates resolver output on configurable subagent.confidence_threshold (default 0.80); below threshold → escalation, at/above → autonomous decision-cooldown.
FEAT Plugin autonomy bumped L1 → L2 (assisted). plugin.sh get_autonomy() now returns 2; new dispatch case on_unknown_prompt routes parser-miss prompts to the resolver chain.
FEAT scripts/escalation_backend.sh (NEW) — escalation sink with two backends: mock (JSONL writer to ~/.local/share/dr-orchestrate/escalation.jsonl) and dev-bot (stub exit 99 with WARN). Frozen JSONL schema documented in tasks/*-fixtures.md — locks the consumer contract for any future dev-bot consumer.
FEAT scripts/rules_loader.sh (NEW) + rules/default.yaml — 3-source rules merge (default → user override → learned-rules stub) with last-write-wins on match-key collisions. Bootstrap ships ~10 slash-command patterns; learned-rules write path is Phase 3 scope.
FEAT scripts/subagent_resolver.sh (NEW) + agents/dr-orchestrate-resolver.md (NEW) — multi-backend resolver implementation + declarative agent spec. Fail-closed semantics: parse failure / backend error / timeout / chain exhaustion → {action:"", confidence:0, reason:"chain_exhausted"}, never an autonomous send.
CHANGE scripts/security.sh — check_cooldown() now wraps the read-write window in flock -n on Linux hosts so concurrent contenders fall through to "blocked" rather than racing the timestamp file. macOS hosts emit a one-time WARN and operate at Phase-1 non-atomic semantics. Added regression for the decision-kind 60 s cooldown.
CHANGE scripts/audit_sink.sh — new make_event_v2 emitter with schema_version: 2 plus confidence, subagent_model, backend_used, escalation_backend, stage (parse / resolve / escalate), outcome (matched / resolved / escalated / blocked_decision_cooldown), and grep-redacted reason. Phase 1 make_event preserved as backward-compatible v1.
CHANGE scripts/semantic_parser.sh — miss path emits source: rule_phase2_miss to distinguish parse-miss from Phase 1 rule-hit. Hit path remains rule_phase1_stub.
FEAT dev-tools/measure-orchestrator-soak.sh (NEW, ~80 LoC) — V-AC-22 soak verdict gate. Computes false_escalate_rate = escalated / (resolved + escalated) over the configurable time window (default 48 h) from schema-v2 audit events; exit 0 if rate < --max-false-escalate threshold (default 0.15).
TEST 21 new bats tests (4 new files: test_rules_loader.bats, test_subagent_resolver.bats, test_escalation_backend.bats, test_cooldown_concurrent.bats) + extensions to test_audit_sink.bats, test_security.bats, test_plugin_register.bats. Full plugin suite: 63 tests, 100% pass on macOS dev host (5 tmux + 2 flock skipped on macOS by design).
DOCS Public-surface sync — plugin.yaml 0.1.0 → 0.2.0, user-config.template.yaml + subagent and escalation stanzas, plugin README.md Phase-2 rewrite, plugin commands/dr-orchestrate.md Phase-2 section, framework CLAUDE.md commands-table entry, framework README.md reference-plugin bullet + version badge, VERSION 2.3.0 → 2.4.0, site data/commands/dr-orchestrate.php EN+RU rewrite, config.php 2.2.0 → 2.4.0.
SECURITY Threat-model controls — fail-closed on all resolver paths (parse-fail / backend-error / timeout / confidence<threshold), least-privilege subprocess invocations (operator user only, no sudo), hash-only credentials invariant preserved, no eval / bash -c "$user_input" in resolver, FD-3 close on all backends (bats-harness deadlock fix), kernel-released flock cleanup (no stale-lock janitor needed).
NOTES v2.4.0 cumulative — Class B (operating-model addition: subagent inference, audit schema v2, autonomy bump). Phase 3 follow-ups (auto-learning rules, real dev-bot consumer, Telegram bridge) remain backlog. Phase 2 ships read-only loader for learned-rules.yaml; write path deferred.

v2.3.0

May 11, 2026

FEAT First non-core plugin: dr-orchestrate Phase 1, a lean tmux runner for advancing a Datarim pipeline one bounded step at a time.
SECURITY Fail-closed input floor with a character allowlist, terminal-escape rejection, two cooldown layers, and a temporary pane block after repeated violations.
SECURITY Operator configuration stays outside git with mode-0600 enforcement. Audit events store a SHA-256 digest of matched pane text instead of the raw text.
TEST Six Bats suites cover the runner, tmux management, parser, security controls, audit sink, and plugin registration. Key injection remains disabled until the operator opts in.

v2.2.0

May 10, 2026

FEAT <TASK-ID> — skills/diataxis-docs.md (NEW). Documentation Taxonomy Mandate: 4 closed Diátaxis categories — tutorials/ (learning), how-to/ (problem-solving), reference/ (lookup), explanation/ (understanding). Closed mapping table covers architecture / testing / deployment / gotchas / api / cli / config / faq / glossary / troubleshooting / examples. 6 anti-patterns explicitly forbidden. Stack-agnostic (no SSG/CMS lock-in).
FEAT <TASK-ID> — templates/docs-diataxis/{tutorials,how-to,reference,explanation}/README.md (NEW, 4 stub files). Per-category onboarding stubs ("when to write here" / "when NOT to write here" / naming convention) used by /dr-init project scaffolding.
FEAT <TASK-ID> — /dr-optimize Step 6 docs-drift detector (commands/dr-optimize.md). Filesystem-presence + threshold ≥3 docs check (Bash, exemption-aware). On drift proposes INFRA-* — Diátaxis docs reorg для <repo> in backlog. Soft warning only; hard CI gate intentionally deferred to a separate backlog item, trigger: ≥3 live consumers post-mandate (same detector flips to exit 1).
CHANGE <TASK-ID> — skills/project-init.md Step 4. Scaffold default replaces flat docs/{architecture,testing,deployment,gotchas}.md with docs/{tutorials,how-to,reference,explanation}/ 4-category split. Legacy stubs auto-mapped per skill mapping table: testing/deployment/gotchas → how-to/, architecture → reference/. Backwards-compat smooth (idempotency rule preserves existing files; never overwrite).
CHANGE <TASK-ID> — code/datarim/CLAUDE.md § Documentation Taxonomy Mandate (NEW section, between Security Mandate and Defensive Invariants). Workspace ~/arcanada/CLAUDE.md § Documentation Taxonomy Mandate added (after Operational Resilience). Both sections point to skills/diataxis-docs.md as single source of truth.
DOCS <TASK-ID> — Public-surface sync: data/skills/diataxis-docs.php NEW (EN+RU), config.php 2.1.0 → 2.2.0, pages/getting-started.php Diátaxis project-scaffolding section, pages/home.php + content/{en,ru}.php stats counts swept skills 39 → 40, framework docs/skills.md + docs/getting-started.md + README.md + project-level CLAUDE.md/README.md updated.
CHANGE <TASK-ID> reframed as first consumer of <TASK-ID> mandate. datarim.club remains pilot site for live deployment of the 4-category taxonomy.
NOTES v2.2.0 cumulative — Class B (operating-model / contract change). PRD-<TASK-ID> ratifies the mandate; comparative analysis vs Google dev docs / Write the Docs / Microsoft Concept-Task-Reference / "no mandate" / "discoverability lint only" alternatives recorded for first time. Hard CI gate deliberately deferred — empirical drift data first.

v2.1.0

May 10, 2026

FEAT <TASK-ID> — /dr-verify tri-layer architecture (v2). Layer 1 deterministic floor (dev-tools/dr-verify-floor.sh, shell pipeline, zero LLM cost) + Layer 2 cross-model peer-review (DeepSeek default via coworker, ~14× cheaper than Sonnet, clean external context — no self-agreement bias) + Layer 3 native runtime dispatch (Claude 3-agent canonical; Codex single-prompt demoted to [experimental] fallback). Findings carry explicit source_layer tag for tri-layer provenance and dedupe.
FEAT <TASK-ID> — New --floor-only + --peer-provider={deepseek,groq,openrouter,...} flags on /dr-verify. --task-id propagation MANDATORY at Layer 2 — without it downstream token-cost / prospective-rate tooling cannot filter logs by task.
FEAT <TASK-ID> — Canonical archive frontmatter template templates/archive-template.md (NEW). Adds verification_outcome block schema (caught_by_verify, missed_by_verify, false_positive, n_a, dogfood_window) — single source of truth for prospective dogfood measurement. /dr-archive Step 2 instructs operator to fill the block.
FEAT <TASK-ID> — Token-cost tooling: dev-tools/measure-invocation-token-cost.sh (per-task aggregation from ~/.local/state/coworker/log/<YYYY-MM-DD>.jsonl, OpenTelemetry-style dotted keys, provider breakdown) + dev-tools/measure-prospective-rate.sh (archive frontmatter aggregator, computes caught_per_5_tasks with decision_hint). Old measure-verify-cost.sh deprecated side-by-side (broken parser shape against current coworker log format).
FEAT <TASK-ID> — /dr-verify provider auto-resolution chain (zero-flag UX). New helper dev-tools/resolve-peer-provider.sh implements a 6-step chain: CLI flag → per-project ./datarim/config.yaml → per-user XDG ~/.config/datarim/config.yaml → coworker --profile code default → cross-Claude-family subagent fallback → same-model isolated last resort. /dr-verify {TASK-ID} now runs end-to-end without an explicit --peer-provider flag.
FEAT <TASK-ID> — Cross-Claude-family fallback. New agents/peer-reviewer.md Sonnet-tier subagent dispatched at chain step #5 in clean isolated context. Covered by Claude subscription, no per-user external API key required. New 3-tier peer_review_mode taxonomy: cross_vendor / cross_claude_family / same_model_isolated.
FEAT <TASK-ID> — templates/datarim-config.yaml (NEW). Per-project datarim-config schema (peer-review provider, cost cap, AAL targets, runtime preferences). Whitelist deepseek | moonshot | openrouter | sonnet | haiku | opus | none blocks malicious-PR typosquat injection at parse time (exit 1 on unknown).
FEAT <TASK-ID> — JSONL emission discipline (Layer 2 reviewer prompts). skills/self-verification.md § Layer 2 mandates suppression of PASS-as-finding entries: findings array carries only defects or incorrect-premise items. Confirmations compress into final-line summary {cleared_iter1: [...], total_new_findings: N}.
FEAT <TASK-ID> — /dr-plan Step 6.5 extension. PRD AC verification commands smoke-checked at plan time against the implemented CLI surface (or pre-implementation skeleton). AC ↔ V-AC semantic match check ensures Validation Checklist rows verify what the AC actually asserts, not just verbatim mirror the AC number.
FEAT <TASK-ID> — Per-mode rate aggregation in dev-tools/measure-prospective-rate.sh. Emits cross_vendor_rate, cross_claude_family_rate, same_model_isolated_rate keys for per-mode dogfood measurement.
CHANGE <TASK-ID> — Brand-hygiene cleanup. Active runtime cross-references to external superpowers:* skill namespace replaced with local Datarim skill names in skills/systematic-debugging.md (3 refs) and skills/finishing-a-development-branch.md (2 refs). External worktree-manager path-interop strings (~/.config/superpowers/worktrees/) removed from cleanup-eligibility list — Datarim runtime owns only .worktrees/ and worktrees/. Lineage from v2.0.0 absorption preserved unchanged in CHANGELOG / PRDs / docs (MIT attribution).
FEAT <TASK-ID> — /dr-plan Phase 4 architectural-superseding probe. Mandatory first sub-step before component breakdown: read archives referenced via Spawned from / Source: and answer whether the architectural problem is already solved by a sibling task. A 30-second grep at planning time prevents dedicated-host plans for problems already absorbed elsewhere.
FEAT <TASK-ID> follow-up — skills/evolution.md § Pattern: Split-Architecture Metrics for Absorption Tasks. Aggregate token budgets fail when absorption adds on-demand files; replaced with idle hot-path + per-existing-file + on-demand-exempt buckets.
FEAT <TASK-ID> — skills/ai-quality.md § Pipeline-Position-Aware AC Formulation. When AC asserts HTTP status, trace request through full middleware/filter chain; if status is downstream of any validator, phrase as semantic gate, not literal status.
FEAT <TASK-ID> — skills/testing.md § Reporting Test Counts in Audit Output. QA/Compliance MUST derive per-spec test counts via mechanical extractor (framework-neutral). skills/compliance.md Step 7 — stale-base merge-result gate: simulate 3-way merge via git merge-tree before flagging a regression from PR diff vs base.
FEAT <TASK-ID> — agents/developer.md resilience-pattern defaults. Circuit-breaker errorFilter: 4xx excluded except 408/429 (downstream pressure signals); breaker.close → self-heal observability event with explicit listener-binding enumeration. L3–L4 tasks: post-final-TDD design-conformance audit listing every event/lifecycle binding against the referenced ADR.
DOCS <TASK-ID> + <TASK-ID> — Public-surface ↔ runtime sync (5-way): data/commands/dr-verify.php + data/agents/peer-reviewer.php (NEW EN+RU), code/datarim/docs/commands.md row, docs/agents.md roster (peer-reviewer added), framework CLAUDE.md /dr-verify rewrite + agent table, README.md feature mention. Counts swept: agents 17→18, skills 27→39, commands 20→22, templates 18→23.
NOTES v2.1.0 cumulative — Class B-lite additive (no breaking changes). <TASK-ID> inherits scope from <TASK-ID> v1 → v2 PRD revision; <TASK-ID> extends without contract change. Findings-only mode preserved at all layers — no auto-fix added. Cross-Claude-family dispatch is first measured tier: empirical bias delta vs same-model self-critique remains under observation in the active dogfood window. Codex CLI degraded mode (CODEX_RUNTIME=1): chain step #5 skipped, step #6 taken with stderr WARN propagated to audit-log.

v2.0.0

May 9, 2026

FEAT <TASK-ID> — Multi-runtime framework (Claude + Codex). New install.sh flag-based architecture: --with-claude, --with-codex, --project DIR, --yes, --dry-run, --force (no flags = print help). Shim creation: install.sh creates ~/.claude/ or ~/.codex/ directories even without runtime binary. --project DIR copy mode rejects system paths (/etc, /usr, /bin, /sbin, /System) with exit 3. Lockfile ~/.${runtime}/.install.lock blocks concurrent runs.
FEAT <TASK-ID> — AGENTS.md symlink → CLAUDE.md. Codex CLI and other runtimes that read AGENTS.md by convention work out of the box, no build step or fork required.
FEAT <TASK-ID> — 14 superpowers skills absorbed. 4 verbatim ports (finishing-a-development-branch, receiving-code-review, systematic-debugging, verification-before-completion); 8 intent-layer rewrites (brainstorming, dispatching-parallel-agents, executing-plans, requesting-code-review, subagent-driven-development, using-git-worktrees, writing-plans, writing-skills) — Claude tool literals (Task() / TodoWrite() / <system-reminder>) replaced with functional prose for runtime-agnostic readability; 2 merges (test-driven-development → testing.md § Discipline; using-superpowers → datarim-system.md § Skill Discovery).
FEAT <TASK-ID> — Per-skill runtime: [claude, codex] + current_aal / target_aal frontmatter on all 38 top-level skills. Classification per AAL Mandate: human-driven idea/design tools 1/2; disciplined process gates 2/3; orchestration / execution-loop skills 2/4. New validator dev-tools/check-skill-frontmatter.sh.
FEAT <TASK-ID> — Token-budget regression gate dev-tools/measure-skill-token-cost.sh. AC-4a idle hot-path: skills/datarim-system.md ≤+16% chars vs v1.23.0 baseline (frozen as .datarim/baseline-v1.23.0.tokens). AC-4b per-existing-file: ≤+30% chars. AC-4c on-demand absorbed files exempt (loaded only when invoked).
FEAT <TASK-ID> — CHANGELOG.md Keep-a-Changelog format introduced; v2.0.0 entry covers full <TASK-ID> ship.
DOCS <TASK-ID> — Honest positioning: multi-runtime framework (Claude + Codex), not "vendor-neutral". Cursor / Goose / Aider — future milestones, not current scope. Codex disclaimer: experience may differ — no Task / TodoWrite primitives; intent-layer rewrites preserve runtime-agnostic readability. Public Surface Scan covers 12 files: README, CLAUDE.md, AGENTS.md, CHANGELOG, docs/*, Projects/Datarim/{README,CLAUDE}, datarim.club {config.php, content/{en,ru}.php, getting-started.php, changelog.php}, ~/.claude/CLAUDE.md global.
CI <TASK-ID> — 41 bats tests GREEN: 29/29 tests/install.bats (legacy invariants <TASK-ID>/0077/0091 preserved) + 12/12 tests/install-tune-0114.bats (no-flags help, --with-claude/--with-codex/multi, --project happy + 3 system-path rejects + missing-arg, --dry-run x2, lockfile concurrency, legacy --copy WARN).
NOTES <TASK-ID> — No breaking changes for existing Claude installs. Refresh via ./install.sh --with-claude. Sub-tasks unblocked: <TASK-ID> (Adversarial Review skill split), <TASK-ID> (Diátaxis reorg), <TASK-ID> (/dr-status pull-mode), <TASK-ID> (Party Mode → Consilium-lite). Follow-ups spawned: <TASK-ID> (project-local evolution learning), <TASK-ID> (Module Manifest — separate task).

v1.24.0

May 7, 2026

FEAT <TASK-ID> — Secure-by-default Network Exposure Baseline. New skill `network-exposure-baseline.md` formalises a four-tier bind-target model (Tier 0 unix-socket / Tier 1 loopback / Tier 2 Tailscale CGNAT / Tier 3 public-with-justification). Tier 3 requires inline `x-exposure-justification` + `x-exposure-expires` (≤90 days). Public-by-default = breach-by-default; loopback/Tailscale binds become the dev/prod default.
FEAT <TASK-ID> — Verifier `dev-tools/network-exposure-check.sh` parses docker-compose ports, redis.conf bind, postgresql.conf listen_addresses, systemd `.socket` ListenStream and Dockerfile EXPOSE; emits text or SARIF. Tiered gate `dev-tools/network-exposure-gate.sh` reads task-description frontmatter (priority/type) and returns `hard_block` / `advisory_warn` / `skip`; missing/malformed frontmatter resolves fail-closed.
FEAT <TASK-ID> — Pipeline integration: `/dr-prd`, `/dr-plan`, `/dr-do`, `/dr-archive` auto-load the skill on network-surface diffs; pre-commit gate in `/dr-do` (Step 8.5) blocks Tier 3 violations or requires `--skip-exposure-gate` override (advisory cases only) with Ops Bot event + § Decisions note. Workspace `CLAUDE.md` § Backend Stack Standards + § CI/CD Convention updated with Tier model + mandatory lint workflow.
CI <TASK-ID> — Reusable workflow `templates/network-exposure-lint.yml` (`workflow_call` with six contract inputs). Drop-in for any service repo; `lint failure ⇒ deploy blocked`. V-AC9 perf budget 30 s; combined run (compose+redis+postgres+systemd) measured p95 ≈ 0.14 s — ~200× headroom.
TEST <TASK-ID> — 59/59 cumulative bats GREEN: 16 P1 verifier (boundary IPv4/IPv6, mapped IPv6, TTL, sub-second perf), 19 tiered-gate, 11 pipeline-command integration, 13 CI workflow integration (structural assertions + 4 fixture-repo simulated runs + V-AC9 perf assertion). actionlint + semgrep p/default + p/secrets + gitleaks all clean.
SECURITY <TASK-ID> — Phase 4 audit of Arcanada-one repos surfaced three production violations spawned as <TASK-ID> (Transcribator PROD compose: `3700:3700` short-form, P0), <TASK-ID> (Auth Arcana dev compose: postgres/redis/app loopback bind, P1), <TASK-ID> (Ops Bot dev compose: postgres/redis loopback bind, P1). Verifier capability gaps (env-interpolation defaults, `${TAILSCALE_IP}:PORT` recognition) tracked as <TASK-ID> / <TASK-ID>.
DOCS <TASK-ID> — `getting-started.php` adds Network Exposure Baseline section (Tier model badges + local check + reusable CI workflow). Workspace + framework CLAUDE.md updated; data/skills/network-exposure-baseline.php published for site n-way sync.

v1.23.0

May 6, 2026

FEAT <TASK-ID> — Plugin System Core: opt-in plugin architecture for Datarim. New CLI `/dr-plugin {list,enable,disable,sync,doctor}` with manifest-driven runtime symlinks. Local plugin sources (absolute path) installed as namespaced symlinks under `~/.claude/{skills,agents,commands,templates}//`. Override mechanism allows root-position installation via `overrides:` field in `plugin.yaml`. `enabled-plugins.md` is the single source of truth for the active set; `dr-plugin sync` reconciles runtime against manifest (orphan removal, broken-symlink recreate, disabled-orphan restore).
FEAT <TASK-ID> — `dr-plugin doctor` ships with 9 health checks: manifest-syntax, inventory-consistency, broken-symlinks, orphan-files, override-integrity, dependency-graph (cycle/dangling DFS), git-state (uncommitted manifest), snapshot-cleanup (>30d), and skill-registry (frontmatter `name:` ↔ basename validation — closes the Skill-tool resolution gap surfaced in Round 4 dogfooding). `--fix` flag auto-repairs checks 2-5 via `cmd_sync` and check 8 via snapshot purge.
SECURITY <TASK-ID> — Pre-mutation snapshot/rollback protocol on every `enable` (V-8). FIFO cap `DR_PLUGIN_SNAPSHOT_MAX=50`; age-based purge via `DR_PLUGIN_SNAPSHOT_AGE_DAYS=30`. Conflict pre-scan rejects symlink loops and cross-plugin shadowing. Critical-core overrides (`evolution`, `datarim-system`, `pre-archive-check`) emit operator-warning to stderr but allow (V-SEC-4). Path traversal, embedded credentials in URLs, and CRLF in YAML rejected at validation gate.
TEST <TASK-ID> — `tests/dr-plugin.bats` 77/77 GREEN across Phases A-D (T1-T135). Coverage: ID/source validation, YAML parsing, list/enable/disable/sync/doctor flows, snapshot/restore, fault injection rollback, override integrity, dependency cycles, skill-registry frontmatter validation. shellcheck -S warning clean.
DOCS <TASK-ID> — `commands/dr-plugin.md` slash-command spec, `templates/plugin.yaml.template` schema (schema_version 1), `templates/enabled-plugins.md.template` runtime manifest schema, README + CLAUDE.md + getting-started.md mention plugin system as opt-in extension mechanism. `data/commands/dr-plugin.php` site page (EN+RU).

v1.22.0

May 3, 2026

FEAT <TASK-ID> — Doc-fanout linter (`code/datarim/dev-tools/doc-fanout-lint.sh`): general N-way consumer-surface drift detector. Three rule kinds: `grep_in_file` (literal pattern with `{name}` substitution), `file_must_exist` (canonicalised path resolution), `count_match` (regex capture group vs glob count). Driven by `.doc-fanout.yml v1` (block-style YAML, depth ≤3). Auto-detected drift fixed in same release: `docs/skills.md` 22→27 reusable skill modules, `docs/agents.md` 16→17 specialized agents, `docs/commands.md` 20→18 slash commands. Plus 13 grep-missing entries added across `CLAUDE.md` and `docs/` for skills/agents shipped without doc rows.
SECURITY <TASK-ID> — Linter ships in `dev-tools/` outside `INSTALL_SCOPES` (whitelist exclusion). Consumer projects of Datarim never receive the linter — no supply-chain footprint. Regression bats `T34/T35/T36` assert exclusion in symlink + copy modes. S1-hardened: `set -u`, regex-validated config strings, `grep -F` literal patterns, path-traversal guard via `canonicalise_path()`, hard caps on config/line size.
TEST <TASK-ID> — `dev-tools/tests/doc-fanout-lint.bats` (17 fixtures: T1–T17 covering parser, all 3 rule kinds, severity gating, output formats, cross-root semantics, `--strict`, install-hook idempotency). `tests/test-command-doc-coverage.bats` (<TASK-ID>) migrated to thin wrapper invoking the new linter via fixture configs; original 4-assertion regression preserved.
CI <TASK-ID> — New `.github/workflows/dev-tools-lint.yml` workflow: `bats-self-tests` (blocking) + `linter-run` (warning-only, cross-root surfaces expected absent in single-repo checkout). Existing `security.yml` 12-job baseline preserved (no path-filter overlap).
DOCS <TASK-ID> — `Projects/Datarim/CLAUDE.md` § Public-surface ↔ runtime sync rule updated from "deferred" to "implemented v1.22.0" with full schema reference. `dev-tools/README.md` documents schema, security boundary, exclusion rationale, pre-commit installer, versioning policy.

v1.21.7

May 3, 2026

DOCS <TASK-ID> — Doc-surface drift sweep: `/dr-doctor` now documented in CLAUDE.md, README.md, docs/commands.md, and docs/getting-started.md. Command was shipped in v1.21.0 but undiscoverable from all documentation surfaces.
DOCS Removed stale `/dr-reflect` reference from CLAUDE.md Pipeline section — reflection was consolidated into `/dr-archive` Step 0.5 in v1.10.0. Removed stale `/dr-security-audit` reference — security review is integrated into `/dr-qa`.
FIX Framework repo `documentation/` directory removed — violates framework/consumer boundary invariant. Consumer projects write task archives to `documentation/archive/`; framework workflow state lives in `Projects/Datarim/datarim/`. Files relocated: `INSIGHTS-<TASK-ID>.md` → `Projects/Datarim/datarim/insights/`; security archives → `~/arcanada/documentation/archive/security/`. Guard added to `.gitignore` to prevent regression.
TEST New bats test `tests/test-command-doc-coverage.bats` — 4 assertions prevent future drift: every `dr-*.md` command file must appear in `docs/commands.md` and `CLAUDE.md`; no obsolete `/dr-reflect` or `/dr-security` refs in `CLAUDE.md`; `documentation/` must not exist in framework repo.

v1.21.6

May 3, 2026

FIX <TASK-ID> — Pass 6 hardening: four parser/dispatch bugs from the v1.21.5 distributed-user report on aether/local-env are fixed. (1) Compound task IDs (e.g. **<TASK-ID>-S8**, **<TASK-ID>-FOLLOWUP-lock-ownership-doc**) now parse via extended ID regex `[A-Z]+-[0-9]+(-[A-Za-z0-9]+)*`. (2) Explicit `→ documentation/archive/{area}/archive-{ID}.md` pointer in bullet body is now preferred over the hardcoded `prefix_to_area(prefix)` mapping — eliminates the duplicate-archive regression where canonical at `general/` and prefix_to_area resolved to `development/`. (3) NEW shape S4 (mid-bold context word, e.g. **<TASK-ID>** soft-delete fix —) recognised. (4) NEW headerless fallback — operational files without `### Recently Archived` header are processed line-by-line; bullets with explicit non-terminal status (in_progress, not_started, blocked, ...) pass through as active content, preserving operator-drift active-task references. (5) Defensive `find documentation/archive/ -name "archive-{ID}.md"` (depth ≤ 3) before synthesise — if canonical exists under any area subdir with the ID literal, strip-with-warning instead of duplicating. Russian archive-section headers (`## Последние завершённые`) now recognised by `is_archive_header`. `validate_task_id` regex extended to accept compound suffixes
DOCS 7 new bats fixtures (T-ARCHIVE-A6-ext, A7, A7b, A8, A9, A9b, A10, T-REPRODUCER): false-positive guard (**TODO**/**FIXME**/**SECTION-1** excluded), explicit-pointer dispatch + path-traversal rejection, compound IDs (<TASK-ID>-S8, <TASK-ID>-FOLLOWUP-*, <TASK-ID> mid-bold), headerless fallback (strip when canonical exists, synthesise when missing), defensive find at unexpected area, distributed-user vault reproducer (14 mixed shapes stripped, zero stubs in development/). Existing T-ARCHIVE-A1..A6 GREEN (no regression). Full bats suite 38 → 45 PASS for datarim-doctor.bats; shellcheck -S warning clean; bandit / gitleaks / anti-pattern grep all zero
DOCS Removed § Pass 6 — Known Issues subsection from skills/datarim-doctor.md (resolved). Updated Pass 6 contract documents four shapes (S1→S2→S4→S3 priority), compound-ID syntax, explicit-pointer dispatch, defensive find, and headerless fallback semantics
DOCS Migration recipe for users on v1.21.5 with stale `documentation/archive/development/` stubs: (1) tarball restore from `/tmp/datarim-backup-*.tgz` reverts datarim/* to pre-fix state; (2) `rm -rf documentation/archive//` if canonical archives live under a different area subdir; (3) re-run /dr-doctor --fix on v1.21.6 — canonical archives auto-detected via defensive find. <TASK-ID> tarball-backup contract unchanged

v1.21.5

May 3, 2026

NEW <TASK-ID> — datarim-doctor.sh now enforces the canonical thin-index contract via NEW Pass 6 — operational-files archive section migration. Strips ## Archived (tasks.md/backlog.md) and ### Archived / ### Recently Archived (activeContext.md) sections that violate the v1.19.1 contract «activeContext.md is one section only — strict mirror of tasks.md § Active; completion history lives in documentation/archive/». For each archive bullet, Pass 6 verifies or synthesises a canonical archive doc at documentation/archive/{area}/archive-{ID}.md, then drops the bullet from the operational file. 91% size reduction on the source-incident reproducer (1626 B → 138 B). Distributed users run /dr-doctor (dry-run) then /dr-doctor --fix and get an explicit per-file summary: parsed/stripped/synthesised/skipped counts
NEW Three archive-bullet shapes auto-detected (S1 arrow-link, S2 status-paren, S3 plain-bold). Per bullet — 4 outcomes: (a) verified canonical archive exists with {ID} literal → strip; (b) canonical archive missing → synthesise stub with frontmatter (id, title, status, date, source: synthesised, original_block_sha) + body = original bullet; (c) collision (existing archive without {ID} literal) → respect --conflict-policy (default --no-prompt skip), preserve bullet with manual-migration marker; (d) unparseable → preserve with warning
NEW Scanner finding dedup — dry-run reports one rolled-up entry per archive section («archive section (N legacy entries — run --fix to migrate to documentation/archive/)») instead of N individual bullet findings. Distributed users see actionable signal, not noise — a typical 14-bullet ## Archived was previously 14 separate finding lines
FIX Reverts 1.21.4 commit (Approach D — whitelist-exception): preserving archive sections by design contradicted the canonical contract and accumulated 12-18 KB token-bloat in operational files (120-540 KB lost tokens per session at 10-30 reads). Approach C (Strip-Or-Synthesise) replaces it after QA BLOCKED Layer 2 (Design Conformance) + PRD-driven re-scope to L3
DOCS 6 new bats cases (T-ARCHIVE-A1..A6): Pass 6 strip-when-verified, synthesise-when-missing, collision-skip-with-marker, activeContext ### Recently Archived end-to-end, idempotency, dry-run rolled-up findings. Suite 31 → 37 PASS, shellcheck -S warning clean
DOCS NEW skills/datarim-doctor.md § Pass 6 — Archive Section Migration with explicit semantics, 3 bullet shapes, 4 per-bullet outcomes, security:counter-example fence rejecting Approach D
DOCS Migration warning for distributed users upgrading from <1.21.5: first `/dr-doctor --fix` after upgrade may synthesise canonical archive docs for orphan bullets in operational files. Tarball backup at /tmp/datarim-backup-*.tgz covers rollback (<TASK-ID> contract unchanged)

v1.21.3

May 2, 2026

NEW <TASK-ID> — datarim-doctor.sh Pass 4 (backlog-archive migration) + Pass 5 (post-fix re-scan) reach POSIX shell parity with the prior ad-hoc Python migration. Approach A: TSV mktemp + AWK section state machine + per-ID dispatch on top of existing extract_*/validate_* primitives. Cancelled entries → documentation/archive/cancelled/archive-{ID}.md; completed entries → verify existing documentation/archive/{area}/archive-{ID}.md or synthesise into general/. Final rm of backlog-archive.md only after migrated == parsed verification
NEW New --no-prompt flag for non-interactive contexts (CI / AI sessions without TTY). Auto-aborts conflicts when target archive already exists without the {ID} literal inside; default interactive behaviour preserved when [ -t 0 ] detects a TTY
NEW Pass 5 post-fix re-scan composition — full dry-run on the migrated tree must report zero findings; per-ID assertion checks every TASK-ID from the pre-fix backlog-archive.md.pre-v2.bak is now represented in documentation/archive/. Mismatch triggers auto-restore from the <TASK-ID> tarball backup
NEW Pre-write per-file sidecar backup datarim/backlog-archive.md.pre-v2.bak preserved after successful migration for forensic provenance, in addition to the <TASK-ID> tarball
DOCS 6 new bats fixtures (T24-T29): Pass4-cancelled (synthesise frontmatter), Pass4-completed-existing (verified, no rewrite), Pass4-completed-missing (synthesise into general/), Pass4-conflict-no-prompt (abort entry to stderr), Pass5-zero-findings (post-fix dry-run + .pre-v2.bak preserved + dry-run exit 0), Pass5-idempotent (second --fix → no-op). Suite 25 → 31 PASS, shellcheck clean, stack-agnostic gate clean
DOCS Real-world dogfood regression on 89kB / 151-entry backlog-archive.md.pre-v2.bak (workspace) — exit 0, 148 archive files synthesised under documentation/archive/, idempotent rerun OK. Confirms bash Pass 4 algorithmic parity with the prior Python migration on production-scale corpus
DOCS Closes the <TASK-ID> v2 consumer-side automation gap. Any project where pre-archive-check.sh Gate v2-A still blocks because of a populated datarim/backlog-archive.md is now a single /dr-doctor --fix away from compliant

v1.21.2

May 2, 2026

NEW <TASK-ID> — NEW scripts/version-consistency-check.sh gate runs as commands/dr-archive.md Step 0.2 between clean-git check and reflect. When VERSION changed in HEAD->working-tree, the script greps CLAUDE.md and README.md for the old version string and blocks archive (exit 1) if any consumer is still stale. Closes the recurring drift class «VERSION bumped but README/CLAUDE.md left at old version»
NEW --allow-version-lag override available for the rare cases where the lag is intentional. Initial-commit and VERSION-unchanged paths are fast no-ops (exit 0), so the gate does not slow down archives that do not bump VERSION
NEW Scope decision: docs/ EXCLUDED. Initial design included docs/ recursive in the scan scope; live-smoke immediately tripped on docs/evolution-log.md citing the prior release. By design, evolution-log / release-notes / changelog are append-only historical ledgers that reference past versions on purpose. Narrowed scope to CLAUDE.md (Version line) + README.md (badge)
DOCS NEW tests/version-consistency-check.bats — 10 cases (T1 unchanged / T2 clean bump / T3 lagging CLAUDE.md / T4 lagging README.md / T5 docs/ excluded by design / T6 --allow-version-lag override / T7 not-a-git-repo / T8 initial bootstrap / T9 whitespace tolerance / T10 no args)
DOCS Lesson — dogfooding > synthetic fixtures. TDD red→green caught the implementation but not the scope error; all 10 synthetic bats cases passed with docs/ in scope because synthetic repos started clean. Live state validates scope; new rule — when a gate is built against a recurring incident class, smoke-test on the live repo before declaring done

v1.21.1

April 30, 2026

NEW <TASK-ID> — history-agnostic cleanup pass complete. All pre-existing task-ID references cleaned from runtime scopes (skills/, commands/) per the heuristic in <TASK-ID>: pure provenance parentheticals deleted, load-bearing rationale anonymised, counter-example incidents kept with neutral phrasing. Final tally — 64 hits in commands/ (9 files) + ~316 hits in skills/ (38 files) eliminated
NEW CI task-id-gate job switched from --diff-only transitional mode to strict full-tree. Pre-existing baseline carry-forward retired; the gate is now the canonical enforcement point for new code
DOCS tests/task-id-gate.bats extended T11-T14 — regression invariants per runtime scope (each scope stays gate-clean over time). 14/14 PASS
DOCS Lesson — bulk regex (Python re.sub over markdown) is NOT fence-aware. Session 3 bulk attempt corrupted teaching content inside a code-fence Examples block; reverted manually. Per-file Edit with explicit fence inspection was the only safe path. Bulk-tool acceleration is forbidden for skills/, commands/, agents/, templates/ markdown going forward — write a fence-aware AST walker first if acceleration is needed

v1.21.0

April 30, 2026

NEW <TASK-ID> — NEW scripts/task-id-gate.sh mirrors the stack-agnostic-gate sibling but enforces a single regex \b[A-Z]{2,10}-[0-9]{4}\b over runtime markdown (skills/agents/commands/templates). Datarim runtime rules are read by AI agents that have no access to the historical context behind each task-ID reference; embedded task-IDs leak into AI outputs addressed to end users
NEW NEW skills/evolution/history-agnostic-gate.md — runtime contract (Trigger, Scope, Denylist, Whitelist, Escape Hatch, markers-must-be-on-separate-lines pitfall, Invocation, Exit codes, Why this exists, Out of scope)
NEW CLAUDE.md Critical Rules § rule 8 — «Rules are stack- AND history-agnostic» — added as durable framework contract
NEW CI integration — 14th job in .github/workflows/security.yml running in --diff-only mode against merge-base HEAD origin/main, so only fresh leakage in the change-set fails CI. Pre-existing baseline references (~339 hits in 57 files) tracked as <TASK-ID> cleanup pass
DOCS NEW tests/task-id-gate.bats + tests/fixtures/task-id-gate/ (5 fixtures) — 10 cases including --diff-only parity. Self-exemption for the gate's own contract document
DOCS Partial cleanup pass at v1.21.0 — agents/developer.md (2 hits) and templates/ (21 hits across 9 files) cleaned; legitimate template placeholders wrapped in escape fences

v1.20.0

April 30, 2026

NEW <TASK-ID> — defence-in-depth data-loss safety contract for /dr-doctor --fix. NEW pre-fix tarball backup at ${DATARIM_DOCTOR_BACKUP_DIR:-/tmp}/datarim-backup-{TS}.tgz (mode 0600 via umask 077). NEW post-fix invariant emitted_count >= parsed_count on the regenerated index — violation triggers auto-restore (rm -rf + tar -xzf) and exit 2
NEW Success summary surfaces the backup path so the operator can recover even after the doctor exits clean. Source incident — external Datarim copy: a 730-LoC rogue datarim-doctor.sh v2 (developed in another worktree, never merged to canonical) was placed directly into ~/.claude/scripts/datarim-doctor.sh. Its --fix destroyed 30 task entries and reported «All fixes applied successfully». Recovery from external tarball
NEW install.sh INSTALL_SCOPES extended (agents skills commands templates) → (agents skills commands templates scripts tests). Both directories now whole-dir-symlinked into ~/.claude/ under default symlink mode — drift between canonical Datarim repo and ~/.claude/ runtime becomes impossible by inode. LOCAL_SCOPES intentionally unchanged (scripts/tests are framework-internal, not user-extensible — local overlay applies only to user-facing scopes)
NEW Whole-directory symlink uniform with skills/agents/commands/templates. Initial implementation tried file-level RUNTIME_SCRIPTS allow-list — rejected at QA review as deviation from established pattern. With dir-symlink, ~/.claude/scripts/ and ~/.claude/tests/ ARE the canonical directories by inode
DOCS tests/datarim-doctor.bats +6 regression tests T16-T21 — backup creation, mode 0600, post-fix invariant on synthetic 3-block fixture, printf hardening (no `printf "$` patterns), body-with-leading-dash safety, summary-prints-backup-path. 21/21 PASS
DOCS Quarantine over edit — rogue ~/.claude/scripts/datarim-doctor.sh (730 LoC) deleted, not patched. Backup at /tmp/rogue-doctor-v2-backup.sh for forensics. Canonical 368 LoC stays the single source of truth — porting v2 features back is a separate decision

v1.19.1

April 30, 2026

NEW <TASK-ID> v2 — operational schema final form. backlog-archive.md ABOLISHED (was a third source of truth duplicating documentation/archive/{area}/archive-{ID}.md). Single source of truth for completion archive = documentation/archive/. Cancelled tasks → new area documentation/archive/cancelled/archive-{ID}.md
NEW activeContext.md § «Последние завершённые» REMOVED ENTIRELY. Pipeline-irrelevant data (only /dr-status displayed it) no longer mutates pipeline-critical file on every /dr-archive. Recency hint moves to runtime: /dr-status --recent N (default 5) computes from documentation/archive/**/archive-*.md mtime-sort. Zero duplication
NEW activeContext.md is now strict mirror of tasks.md § Active — identical lines, identical order. ≤30 lines. pre-archive-check.sh validates equality and line-format
NEW pre-archive-check.sh v2 hard gates: (a) forbidden-file detector blocks progress.md / backlog-archive.md presence; (b) forbidden-section detector blocks ## Последние завершённые / ## Last Completed; (c) line-format gate extended to activeContext.md § Active Tasks (catches paragraph-form leak). 5 new bats fixtures (T37-T41), 40/40 PASS
NEW /dr-archive Step 6 simplified — Prepend Last Completed + cap-at-20 logic removed. /dr-archive becomes ~10 LoC shorter; activeContext.md no longer mutated for display-only data
NEW /dr-status --recent N flag — runtime computation of recently-completed tasks. POSIX one-liner: ls -t documentation/archive/**/archive-*.md | head -N. Stack-agnostic, no dependencies
DOCS CLAUDE.md § Datarim State Directory tree updated — backlog-archive.md and progress.md removed; new cancelled/ area added to archive tree
DOCS skills/datarim-system/backlog-and-routing.md rewritten — Two-File → Single-File Architecture. backlog.md is the only operational backlog file; archived tasks leave to documentation/archive/
DOCS skills/datarim-system.md § activeContext.md thin contract simplified — one section only (Active Tasks mirror)
DOCS templates/activeContext-template.md rewritten (one section); templates/backlog-template.md cancelled-block comment updated
DOCS Workspace dogfood (<TASK-ID> v2 itself): activeContext.md 37 paragraph-form lines → 25 thin lines; backlog-archive.md 1013 lines → DELETED; 12 missing per-task archive files synthesised in documentation/archive/ for prior gaps; 153/153 archive coverage verified

v1.19.0

April 30, 2026

NEW Operating-model change: operational files (tasks.md, backlog.md, activeContext.md) become THIN INDEXES — one-liner-per-task with pointer to externalised description file. Full task body (Overview, ACs, Constraints, Out of Scope, Related) lives in datarim/tasks/{TASK-ID}-task-description.md with closed 12-key YAML frontmatter (id, title, status, priority, complexity, type, project, started, parent, related, prd, plan). Canonical regex: ^- ([A-Z]{2,10}-[0-9]{4}) · (status) · P[0-3] · L[1-4] · (.{1,80}) → tasks/\1-task-description\.md$. Closes the «3000+ line monolithic operational files» problem — agents read 24-line index instead of 9000-line monolith (<TASK-ID>)
NEW progress.md ABOLISHED — its single «Last Updated» paragraph was the dominant single-hunk diff that broke `git add -p` patch-staging in shared workspace. Last-completed log moves to activeContext.md § Последние завершённые (cap raised 10 → 20 entries; older entries remain in documentation/archive/) (<TASK-ID>)
NEW NEW /dr-doctor command — diagnoses and migrates legacy block-style entries (### TASK-ID:) to thin schema. Idempotent (re-run = no-op). 4-pass migration: descriptions cache → operational rewrite → activeContext convert → progress.md retire. Path-traversal guard via lib/canonicalise.sh, lockfile via flock. CLI: --fix / --scope / --root / --task-id / --quiet / --no-color / --help. Exit codes 0/1/2/3/4/64 (<TASK-ID>)
NEW NEW skills/datarim-doctor.md — schema spec + migration semantics. Loaded on demand by /dr-doctor and /dr-init Step 2.4 self-heal. Documents canonical regex, YAML frontmatter contract, conflict resolution, edge cases (bash 3.2 macOS default, →-in-title, concurrent invocation) (<TASK-ID>)
NEW /dr-init Step 2.4 STRUCTURAL COMPLIANCE CHECK — probes datarim-doctor.sh --quiet on every init when datarim/ already exists. exit 1 + TTY → prompt «Run /dr-doctor --fix? [Y/n]» (default Y). Non-tty → warn-continue. exit 2/3/4 → ABORT (corrupt state, lock contention, security violation). Self-heal entry point closes the loop (<TASK-ID>)
NEW pre-archive-check.sh schema-compliance gate — validates every bullet line in REPO/datarim/{tasks,backlog}.md against canonical regex; flags legacy ### TASK-ID: blocks. Auto-skip when repo lacks datarim/. Hooked into both shared-mode and legacy-mode success paths. Escape: --no-schema-check (in-flight migration only) (<TASK-ID>)
NEW Description File Contract — closed 12-key YAML frontmatter schema, 5-section markdown body capped at 250 lines (Overview / Acceptance Criteria / Constraints / Out of Scope / Related, optional Implementation Notes / Decisions). Anything beyond → split into PRD or design doc (<TASK-ID>)
NEW scripts/lib/canonicalise.sh extracted as shared library — lexical path canonicalisation (no I/O), reused by check-doc-refs.sh and datarim-doctor.sh. Closes <TASK-ID> reflection Proposal A2 (N=2 spawn-trigger met)
DOCS skills/datarim-system.md +87 lines: §§ Operational File Schema / Description File Contract / activeContext.md Write Rules / Self-Heal Entry Points
DOCS commands/dr-archive.md, dr-plan.md, dr-do.md, dr-status.md updated for thin-index ops — never writes progress.md, parses one-liner regex, lazy-loads description files
DOCS templates/{backlog,task,activeContext}-template.md REWRITTEN — backlog three sections (Pending/Blocked-Pending/Cancelled), task with 12-key frontmatter, activeContext NEW thin-format template
DOCS tests/datarim-doctor.bats — 15 cases (compliance detection, migration, security path-traversal, regex compliance, CLI/UX). tests/pre-archive-check.bats: 33 → 36 cases (+3 schema gate fixtures). Full bats regression: 71/71 PASS, shellcheck clean, stack-agnostic gate clean across all touched files
DOCS Self-dogfood on Arcanada workspace: tasks.md 3017 → 24 lines, backlog.md 2109 → 201 lines, progress.md 4286 lines DELETED, 239 description files generated. Net -9205 lines across 3 tracked operational files. Idempotency confirmed (second --fix run exits 0 silently)

v1.18.4

April 29, 2026

NEW scripts/pre-archive-check.sh — DATARIM_PRE_ARCHIVE_WHITELIST env-var extension. Consumers can extend the hardcoded <TASK-ID> whitelist (VERSION, CHANGELOG.md, package.json, Cargo.toml, pyproject.toml, .gitignore) with project-specific version-bump basenames (e.g., config.php) via PATH-style colon-separated env-var, without modifying the framework. Path components are rejected (basename match only). Closes the gap surfaced in <TASK-ID> self-dogfood — Projects/Websites/datarim.club/config.php is a legitimate Datarim public-surface version-bump file but its basename does not belong in the canonical hardcoded list shipped to all consumers (<TASK-ID>)
NEW --no-whitelist continues to override both the hardcoded list AND env-var entries — strict default-deny preserved for paranoid contexts
NEW commands/dr-archive.md Step 0.1.2 footnote on the whitelisted row documents the env-var extension, the PATH-style format, the basename-only contract, and precedence vs --no-whitelist
DOCS tests/pre-archive-check.bats: 28 → 31 tests (+3 <TASK-ID> fixtures — env-var single basename → whitelisted; env-var colon-separated multi-basename → all entries whitelisted; --no-whitelist overrides env-var → unattributed restored)
DOCS docs/evolution-log.md <TASK-ID> entry — Class A additive runtime behaviour; spawn-trigger N=2 reached (<TASK-ID> hardcoded list + <TASK-ID> self-dogfood gap); sixth iteration of the «Memory Rule → Executable Gate at Apply Step» pattern (<TASK-ID>/0056/0058/0059/0060/0061); backwards-compatible by design (T1-T28 fixtures all pass; env-var unset → no behaviour change)

v1.18.3

April 29, 2026

NEW scripts/pre-archive-check.sh — 6-th hunk classification "mine-by-elimination" added. When --task-id is set, the file has actual diff lines, AND those diff lines (additions/removals) contain ZERO task IDs while the committed body carries foreign historical IDs, the gate attributes the edit to the current task and exits 0. Closes the false-foreign misclassification of doc edits like CLAUDE.md, README.md, and architectural docs where the body references many historical tasks but the current edit (e.g., a version-line bump) introduces none. Founding incident: <TASK-ID> archive — code/datarim/CLAUDE.md and README.md version-bump 1.18.0 → 1.18.2 misclassified as foreign despite diff lines being clean (<TASK-ID>)
NEW Safety guard: untracked files (no diff at all) skip the mine-by-elimination branch and fall through to existing "foreign" classification. Operator visibility preserved — the new klass surfaces in stdout with the foreign body IDs listed for review at patch-staging time
NEW commands/dr-archive.md Step 0.1.2 — classification contract paragraph extended with the mine-by-elimination klass and its untracked-files safety-guard note
DOCS tests/pre-archive-check.bats: 25 → 28 tests (+3 <TASK-ID> fixtures — body has foreign IDs + diff lines clean → mine-by-elimination + exit 0; diff lines contain TASK_ID → mixed not mine-by-elimination; diff lines contain only foreign IDs → foreign not mine-by-elimination)
DOCS docs/evolution-log.md <TASK-ID> entry — Class B operating-model extension; spawn-trigger N=2 reached by explicit human approval (<TASK-ID> self + CLAUDE.md/README.md observed misclassification = second class instance); fifth iteration of the «Memory Rule → Executable Gate at Apply Step» pattern (<TASK-ID>/0056/0058/0059/0060); backwards-compatible (T1-T25 fixtures all pass; full repo regression 38/38 PASS)

v1.18.2

April 29, 2026

NEW scripts/pre-archive-check.sh — 5-th hunk classification "whitelisted" added. When --task-id is set and a modified file's basename matches the hardcoded version-bump list (VERSION, CHANGELOG.md, package.json, Cargo.toml, pyproject.toml, .gitignore), the gate accepts it without a task-ID inside the diff. The operator-supplied --task-id is the attribution. Closes the false-positive surfaced during <TASK-ID> self-dogfood — VERSION is a single-line file that physically cannot carry a task ID (<TASK-ID>)
NEW --no-whitelist escape flag restores strict default-deny for paranoid contexts. Without --task-id (legacy mode), whitelist is not active at all
NEW commands/dr-archive.md Step 0.1.2 — classification contract paragraph extended with the whitelisted klass and the basename list
DOCS tests/pre-archive-check.bats: 22 → 25 tests (+3 <TASK-ID> fixtures — VERSION + --task-id → exit 0 whitelisted; --no-whitelist + VERSION → exit 1 unattributed restored; non-whitelisted basename → default-deny preserved)
DOCS docs/evolution-log.md <TASK-ID> entry — Class B operating-model extension; founding incident <TASK-ID> self-dogfood; backwards-compatible (T1-T22 fixtures all pass)

v1.18.1

April 29, 2026

NEW scripts/pre-archive-check.sh — conditional-shared auto-detect: when invoked with --task-id and the positional repo has a .datarim-shared marker file at root, route to shared-mode classification automatically (no explicit --shared flag needed). Closes the gap surfaced during <TASK-ID> self-dogfood — framework repo Arcanada-one/datarim itself is multi-agent but was single-agent-classified by default (<TASK-ID>)
NEW .datarim-shared marker file shipped at framework repo root — opt-in signal that a repo carries cross-task hunks from parallel agent sessions. Portable across forks/mirrors (origin-URL match was rejected as fragile)
NEW commands/dr-archive.md Step 0.1.1 — classification table extended with a new Conditional-shared row (marker + --task-id auto-detect). Step 0.1.2 invocation form now documents both explicit --shared and auto-detect paths
DOCS tests/pre-archive-check.bats: 19 → 22 tests (+3 <TASK-ID> fixtures — marker auto-detect with foreign hunks → exit 0; marker absent + dirty → legacy STOP; marker + own hunks → exit 1 own classification)
DOCS docs/evolution-log.md <TASK-ID> entry — Class B operating-model extension; backwards-compatible (project repos without marker keep <TASK-ID> strict legacy behaviour)

v1.18.0

April 29, 2026

NEW /dr-archive Step 0.1 promoted to multi-agent shared workspace semantics — foreign-task hunks from parallel agent sessions are no longer false-positive blockers; only the current task's own forgotten hunks (or unattributed hunks) block (<TASK-ID>)
NEW scripts/pre-archive-check.sh extended with --task-id --shared flags — classifies each modified file's hunks as own / foreign / mixed / unattributed; legacy single-agent mode unchanged (<TASK-ID>)
NEW commands/dr-archive.md Step 0.1 rewritten with sub-steps 0.1.1–0.1.5 (repo classification, shared check, patch-staging recipe, retry-tolerant pre-commit re-verify, project repo legacy check)
NEW CLAUDE.md § Workspace Discipline (multi-agent) — runtime-loadable summary of Step 0.1 contract for AI agents
DOCS tests/pre-archive-check.bats: 12 → 19 tests (7 new <TASK-ID> cases — foreign-only, own, mixed, unattributed, invalid id, missing --shared, legacy regression)
DOCS docs/evolution-log.md <TASK-ID> entry — Class B operating-model contract change, founding incidents <TASK-ID> / <TASK-ID> / <TASK-ID>

v1.17.2

April 27, 2026

FIX Stack-agnostic gate: 32 hits across 11 runtime files cleaned (4 reword, 4 wrap with block-style markers, 2 whitelist additions, 1 hybrid). Gate now exits 0 across all four scopes — skills/, agents/, commands/, templates/ (<TASK-ID>)
FIX Reworded npm/pip/cargo audit references in skills/security.md, skills/project-init.md, agents/researcher.md, commands/dr-qa.md to neutral phrasing «package-manager-native audit command at the declared severity threshold»
FIX Whitelist additions: skills/testing/live-smoke-gates.md (<TASK-ID>/1169 incident postmortems with stack-specific lifespan semantics) and skills/utilities/ga4-admin.md (Python-specific GA4 Admin API recipe) — both meet the 4 whitelist criteria from gate-spec § «When to add a file to the Whitelist»
FIX Inline-marker pitfall surfaced and documented: gate-spec markers MUST be on their own lines; awk strip uses next after opening match, so closing marker on the same line is never processed → skip persists. Logged as Class A apply candidate for next /dr-archive Step 0.5
DOCS docs/evolution-log.md <TASK-ID> entry — full sweep cleanup table (10 changes), verification block (gate ×4 PASS clean, bats baseline 158/160, 2 reds pre-existing), pattern-level Class A candidates
DOCS Recurrence loop closed: <TASK-ID> → <TASK-ID> → <TASK-ID> → <TASK-ID> → <TASK-ID>. Datarim runtime is now stack-agnostic with zero gate violations across all four scopes.

v1.17.1

April 26, 2026

FIX Bats baseline cleanup — removed 6 stale assertions covering deleted artefacts (agents/optimizer.md old 6-section schema, removed go-to-market.md, snapshot "24 skills" count) so the test suite now reflects live invariants only (<TASK-ID>)
FIX reflect-removal-sweep whitelist extended with skills/evolution/class-ab-gate.md and skills/evolution/examples-and-patterns.md — fragment files inherit their parent's historical /dr-reflect references (<TASK-ID>)
FIX skills/evolution.md gained an explicit v1.10.0 / <TASK-ID> forward-pointer note + cross-reference to skills/utilities/recovery.md (<TASK-ID>)
FIX skills/file-sync-config.md description trimmed from 339 → 133 chars to honour the 155-char discovery cap (<TASK-ID>)
DOCS docs/evolution-log.md <TASK-ID> entry rephrased to drop literal "dr-reflect" substring outside the whitelist (<TASK-ID>)
DOCS Final test result: 154 pass / 0 fail / 154 total — first clean baseline since v1.10.0

v1.17.0

April 25, 2026

NEW Symlink-default install mode — install.sh now creates symlinks for agents/skills/commands/templates by default; runtime IS the repo, drift is impossible by definition (<TASK-ID>)
NEW New --copy flag preserves legacy real-copy behaviour for Windows/FAT/restricted shells; auto-detected on MINGW/MSYS/CYGWIN
NEW Local overlay — new ~/.claude/local/{skills,agents,commands,templates}/ gitignored layer for personal additions and overrides
NEW Migration prompt — existing v1.16 copy installs see an interactive [c]onvert / [k]eep / [a]bort prompt on first v1.17 install; --yes auto-converts with backup
NEW update.sh runtime-aware — symlink topology exits after git pull, copy topology runs install --copy --force --yes (preserves user mode)
NEW validate.sh local-override warning — emits "WARN: override detected" per file in local/ that shadows a framework file
NEW install.sh --force is a documented no-op under symlinks (prints "Already symlinked, nothing to update")
CHANGE curate-runtime.sh and check-drift.sh marked DEPRECATED in v1.17, removal in v1.18 (<TASK-ID>)
CHANGE check-drift.sh exit-code: symlink → repo now exits 0 (sync by definition); symlink → other path is real drift (exit 1)
DOCS docs/getting-started.md § Installation rewritten: symlink default + --copy fallback + Windows note + local/ overlay + migration prompt
DOCS skills/datarim-system.md § Loading Order documents framework + overlay layering and conflict-resolution rule
DOCS 16 new bats tests cover AC-1..AC-9 (symlinks, --copy, Windows fallback, migration c/k/a, --force no-op, drift exit codes, validate WARN, deprecation banners) — final 150 pass + 10 pre-existing fail

v1.16.0

April 25, 2026

NEW Unified CTA "Next Step" block — every /dr-* command now ends with a canonical block: resolved task ID, numbered options, exactly one **рекомендуется** primary marker, --- HR wrapping (<TASK-ID>)
NEW Multi-task awareness (Variant B) — when more than one task is active, the CTA appends a "Другие активные задачи" menu with the recommended next command for each parallel task
NEW FAIL-Routing CTA variant — /dr-qa BLOCKED and /dr-compliance NON-COMPLIANT now emit a CTA naming the explicit layer-return command + task ID (no more free-text routing)
NEW New skills/cta-format.md — single source of truth canonical specification, loaded by planner, architect, developer, reviewer, compliance agents
NEW New templates/cta-template.md — reusable Markdown snippet with placeholders for the three CTA variants
DOCS Updated 17 commands with unified ## Next Steps (CTA) section + 5 agents with cta-format in Context Loading
DOCS Visual maps: added CTA decision-point diagrams to pipeline-routing.md and CTA-emission map to stage-process-flows.md
DOCS backlog-and-routing.md: Mode Transition table now references cta-format and documents Layer-to-command map for FAIL-Routing
DOCS New tests/cta-format.bats — 39 spec-regression tests + 3 golden fixtures (single-task, multi-task, fail-routing)
DOCS Anti-pattern guard: tests now fail if any command file uses U+2500 box-drawing as separator (Windows mojibake risk per Claude Code issue #34247)

v1.15.2

April 24, 2026

FIX curate-runtime.sh: fixed infinite loop in interactive mode when stdin is not a TTY (non-interactive terminal, pipe, tmux)
FIX curate-runtime.sh: portable sed — replaced BSD-only sed -i '' with temp file + mv (fixes version bump on GNU/Linux/RedHat)
FIX curate-runtime.sh: skip-rest (s) now actually skips remaining files in current scope instead of acting as single-file skip
FIX curate-runtime.sh + check-drift.sh: symlink detection — warns when runtime dirs are symlinks to repo (drift detection impossible)
NEW curate-runtime.sh: TTY guard for interactive mode — clear error message with --auto/--dry-run suggestions
NEW curate-runtime.sh: EOF guard in prompt — prevents infinite loop on closed stdin
DOCS 5 new bats tests: non-TTY rejection, --auto without TTY, symlink detection (curate + drift), portable sed verification

v1.15.1

April 24, 2026

FIX Split evolution.md (413→215 lines) into entry + 3 fragments: class-ab-gate, disaster-recovery, examples-and-patterns
FIX Split ai-quality.md (394→173 lines) into entry + 2 fragments: incident-patterns, deployment-patterns — all content preserved
FIX Shortened 16 component descriptions to ≤155 chars — total budget 8085→7000 chars (under 8000 threshold)
FIX Slimmed skill-creator agent (153→95 lines) and optimizer agent (139→50 lines) — both under 120-line warn threshold
DOCS Optimization audit report saved to datarim/reports/optimize-audit-2026-04-24.md
DOCS Evolution log updated with 5 OPT-004 entries

v1.15.0

April 23, 2026

NEW Research Phase 1.3 in /dr-prd — structured external context research for L2+ tasks (<TASK-ID>)
NEW Gap Discovery Step 7.5 in /dr-do — auto-spawns researcher agent when implementation hits unknowns
NEW New researcher agent (17th) — investigates library versions, best practices, CVEs, compatibility via adaptive tooling
NEW New research-workflow skill (22nd) — 10-point full checklist (L3-L4), 5-point lite mode (L2), gap discovery protocol
NEW New insights-template (13th) — 7-section document for research results, separate from PRD
NEW Insights document: datarim/insights/INSIGHTS-{task-id}.md — living artifact, updated during implementation
NEW /dr-plan auto-loads insights document as context when available
NEW Discovery interview reads insights before proposing answers — research-informed requirements
DOCS Visual maps updated: pipeline routing annotations, stage process flows, dependency graphs
DOCS path-and-storage: datarim/insights/ directory added to core directories
DOCS backlog-and-routing: embedded phases section documenting research and gap discovery

v1.14.0

April 22, 2026

NEW Project scaffolding in /dr-init — create full project structure with CLAUDE.md, docs/, datarim/ via "/dr-init create project Name"
NEW New project-init skill — auto-detects tech stack, creates docs stubs (architecture, testing, deployment, gotchas), ephemeral working dirs
NEW New CLAUDE.md project template — Laws of Robotics + Datarim pipeline + project-specific placeholders
NEW New docs stubs template — 4 documentation files with structured placeholders
NEW Intent detection: /dr-init auto-routes between project scaffolding and task creation based on prompt keywords
NEW Idempotent scaffolding — safe to run on existing projects, skips existing files
DOCS dr-help updated with Project Scaffolding section and examples
DOCS Skill count 24→25, template count 11→13

v1.13.1

April 19, 2026

NEW New /dr-publish command — content pipeline now complete: /dr-write → /dr-edit ⇄ /dr-write → /dr-publish → /dr-archive
NEW New publishing skill — universal technical rules for 6 social platforms (Telegram, LinkedIn, Facebook, X/Twitter, VK, Instagram) + website publishing (OG tags, blog checklist)
NEW /dr-dream now scans documentation/archive/ in addition to datarim/ — task archives are part of the knowledge base
BREAKING telegram-publishing skill replaced by publishing (broader scope, same Telegram rules preserved + 5 new platforms)
FIX Content pipeline gap closed — previously no step between editorial review and archive for formatting/publishing
DOCS Visual maps updated: content pipeline flow diagram, command-agent-skill dependency graphs
DOCS Command count 18→19, Content category 2→3 commands

v1.13.0

April 19, 2026

NEW tasks.md size guard (<TASK-ID>): warn at 3K lines, hard stop at 5K — prevents undetected file bloat (10K→2.5K cleanup preceded this)
NEW Content discipline: explicit allowed/prohibited content types for tasks.md — credentials, specs, templates must go to dedicated files
NEW L3-L4 plan extraction: large plans written to datarim/plans/{ID}-plan.md instead of inline — keeps tasks.md lean
NEW Concurrent write safety: timestamp-based conflict detection for multi-session work on tasks.md
NEW Cross-repo atomicity ADR (<TASK-ID>): R1+R7 "same commit" rule relaxed for cross-repo — "same session + same day + cross-cite" now valid
NEW Optimizer health metrics (<TASK-ID>): tasks.md and activeContext.md line counts added to /dr-optimize dashboard
BREAKING Skills consolidated 24→20 (<TASK-ID>): infrastructure-debugging + remote-measurement merged into infra-automation, go-to-market merged into writing, incident-investigation pruned
FIX /dr-archive Step 7: task body fully deleted instead of preserved in HTML comments — archives are the permanent record
FIX activeContext.md pruning: "Последние завершённые" capped at 10 entries
DOCS ADR-<TASK-ID>: formal decision record for cross-repo contract-implementation atomicity
DOCS evolution.md: Contract-Implementation Atomicity section added (anti-<TASK-ID> rule formalized)

v1.12.0

April 18, 2026

FIX Pipeline routing incident (<TASK-ID>): fixed 4 defects where Design, QA, and Compliance steps were silently skipped for L3-L4 tasks
FIX /dr-plan now correctly routes L3-4 tasks to /dr-design instead of /dr-do
FIX /dr-qa verdict table: ambiguous "compliance or archive" replaced with explicit complexity-based routing
FIX L3 pipeline: compliance step is now mandatory (was incorrectly marked as conditional)
NEW QA FAIL conditional routing (<TASK-ID>): BLOCKED verdict now routes by earliest failed layer — L1→/dr-prd, L2→/dr-design, L3→/dr-plan, L4→/dr-do
NEW Loop guard: if the same QA layer fails 3 times, escalate to user with options (force-pass / reduce scope / cancel)
NEW Re-entry rules: after FAIL fix, resume forward through pipeline; QA must be re-run with -v2 suffix on report
NEW Compliance NON-COMPLIANT now has source-aware routing (PRD gap → /dr-prd, code issues → /dr-do)
NEW Consilium waiver: /dr-design can skip panel when one option clearly dominates all tradeoffs
NEW PRD-datarim-sdlc-framework.md: canonical pipeline contract created — single source of truth for all routing rules
DOCS Visual maps updated: QA diagram shows layer-based FAIL branches, pipeline diagram shows L3 compliance as mandatory
DOCS backlog-and-routing.md: FAIL Return Routing section added to Mode Transitions

v1.11.0

April 18, 2026

BREAKING seo-launch and marketing skills merged into go-to-market (<TASK-ID>) — update any references in project CLAUDE.md files
NEW Task Resolution Rule: automatic disambiguation when multiple tasks are active simultaneously (<TASK-ID>)
NEW Multi-task active context: /dr-init appends, /dr-archive removes — no command overwrites the active task list
NEW curate-runtime.sh: automated runtime-to-repo sync script with interactive/auto/dry-run modes (<TASK-ID>)
NEW 4 new skills: reflecting, infra-automation, infrastructure-debugging, go-to-market
NEW PRD waiver check: Level 3-4 tasks now prompt for PRD or explicit waiver reason (<TASK-ID>)
NEW /dr-plan fixture capture: mandatory live CLI/API output sampling when parsing external tool responses
DOCS Description optimization: 63% reduction in total description characters (<TASK-ID>)
DOCS Full README rewrite for both project and repository documentation
DOCS All datarim.club pages updated to reflect v1.11.0 state
MIGRATION If your project CLAUDE.md references seo-launch or marketing skills — replace with go-to-market

v1.10.0

April 16, 2026

BREAKING /dr-reflect command removed — reflection now runs automatically inside /dr-archive as mandatory Step 0.5 (<TASK-ID>)
NEW Pipeline shrinks from 9 stages to 8 stages; reflection is no longer skippable
NEW New skills/reflecting.md — the reflection workflow is preserved as a skill invoked internally by /dr-archive
NEW /dr-archive Step 0.5 loads reflecting.md, generates lessons learned, Class A/B evolution proposals, health-metrics check, follow-up tasks
NEW STOP on failure — if reflection fails or Class A proposals are rejected, archive halts (idempotent re-run)
DOCS README.md, CLAUDE.md, pipeline.md, commands.md, agents.md, skills.md, evolution.md, getting-started.md, use-cases.md all updated to 8-stage pipeline
DOCS Visual-maps regenerated: 4 mermaid diagrams updated for v2 pipeline contract
DOCS 3 new bats spec-regression tests (T1/T2/T3) guard against silent weakening
MIGRATION If your scripts or CI invoke /dr-reflect directly — replace with /dr-archive. Reflection content and behavior are unchanged; the invocation path is now automatic.

v1.6.0

April 13, 2026

NEW Unified Task Numbering: same ID across backlog, task, and archive (no more BACKLOG-XXXX → TASK-XXXX rename)
NEW Model Assignment Convention: each agent and task-skill specifies its model (opus/sonnet/haiku)
NEW Cost optimization: 6 opus + 9 sonnet + 1 haiku agents (was 16 opus)
NEW 14 task-skills now have explicit model field; 6 reference-skills inherit
NEW skill-creator requires model field in new agents and task-skills
DOCS Backlog workflow guide updated for unified ID convention
DOCS Model Assignment Convention documented in datarim-system.md

v1.5.0

April 12, 2026

NEW Universal Platform QA Tester agent (16th agent)
NEW Archive reorganization: documentation/archive/{area}/ with topic-based organization
NEW /dr-init creates documentation/archive/, adds datarim/ to .gitignore
NEW /dr-prd generates backlog items from PRD
NEW Dream skill expanded to scan documentation/archive/
DOCS Backlog workflow guide for project managers
DOCS Getting started guide with .gitignore philosophy

v1.4.0

April 10, 2026

NEW Migrated to GitHub (Arcanada-one/datarim)
NEW install.sh for automated setup
NEW 19 commands, 15 agents, 18 skills (in v1.4.0)

v1.3.0

April 8, 2026

NEW /dr-write and /dr-edit commands for content creation
NEW /factcheck and /humanize autonomous skills
NEW Writer and Editor agents
NEW Writing workflow with editorial review

v1.2.0

April 6, 2026

NEW Migrated from memory-bank to datarim naming
NEW /dr-dream knowledge base maintenance
NEW /dr-optimize framework auditing
NEW Backlog two-file system (active + archive)

v1.1.0

March 31, 2026

NEW Consilium multi-agent panel discussions
NEW Strategist agent for Value/Risk/Cost analysis
NEW Discovery interview skill
NEW /dr-addskill for creating new framework components

v1.0.0

March 23, 2026

NEW Initial release — 9-stage pipeline
NEW Core agents: planner, architect, developer, reviewer
NEW Task tracking with complexity levels (L1-L4)
NEW Self-evolution through /dr-reflect