Features
Everything you need to run AI-assisted projects at any scale
8-Stage Pipeline
Not every task goes through all stages. A simple fix: init → do → archive (archive runs reflection automatically as Step 0.5). A major project: all 8 stages with multi-agent review.
Analyze task or scaffold project, determine complexity (L1-L4), create tracking
Product requirements with research phase (1.3) and discovery interview
Detailed implementation plan with strategist review
Architecture exploration for complex features (L3-4)
TDD implementation with gap discovery for unknowns
4-layer quality check: PRD, design, plan, code
Adaptive post-QA hardening by task type
Step 0.5 reflection (lessons + evolution proposals), then archive
18 Specialized Agents
Each agent has a focused role — from planning to security audit. They collaborate through the pipeline, and Consilium brings them together for critical decisions.
Chief Architect for system integrity, scalability, and alignment with architectural patterns. Leads context gathering, solution exploration, and user consultation.
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Runs the post-QA hardening workflow (7 steps): re-validate vs PRD/task, simplify code, check references/coverage/lint/tests, produce compliance report.
Senior Developer implementing features with TDD and high code quality. Follows project patterns and style guide.
DevOps Engineer owning the build-ship-run pipeline from code commit to running in production.
Content Editor for editorial review, fact verification, AI pattern removal, and publication-ready quality. Works with articles, blog posts, social media, research papers, and documentation.
Knowledge Base Librarian for organizing, indexing, cross-referencing, and maintaining the datarim/ directory. Runs ingest, lint, and consolidation workflows to keep the knowledge base healthy and navigable.
Audit and improve the Datarim framework: detect bloat, duplicates, oversized files, weak descriptions, and selective-loading opportunities.
Adversarial reviewer subagent for /dr-verify Layer 2/3 cross-Claude-family fallback. Reviews PRD/plan/code in clean isolated context. Findings-only, read-only tools.
Lead Project Manager for backlog management, detailed design, implementation plans, and complexity levels.
Investigates external context — library versions, best practices, CVEs, compatibility — before planning begins and when implementation hits unknowns.
QA and Security Lead for code reviews, security compliance, and Definition of Done validation.
Security Analyst identifying, assessing, and mitigating security risks throughout the development lifecycle.
Skill Creator agent for researching, designing, and generating new skills, agents, and commands. Analyzes best practices, audits existing framework components, and creates or updates artifacts in the correct location.
Site Reliability Engineer ensuring systems are reliable, observable, and recoverable in production.
Strategic Advisor evaluating whether a task is worth building and proposing the most efficient path.
Platform QA agent for verifying changes across any project. Auto-detects test runners, supports Docker-aware execution, API smoke tests, and structured result reporting.
Content Writer for creating articles, blog posts, social media content, research papers, technical documentation, and any structured written output. Focuses on clear, engaging, audience-appropriate writing.
26 Commands
Slash commands drive the pipeline — 8 pipeline stages, content, management, utility, autonomous.
datarim
CLI
External-agent surface — non-interactive CLI that drives the full Datarim pipeline through HTTP webhook (AAL 3 opt-in)
/dr-addskill
Manage
Create or update skills, agents, and commands
/dr-archive
Pipeline
Archive completed task with mandatory reflection and evolution proposals
/dr-auto
Pipeline
Autonomous-execution meta-command — runs the full pipeline end-to-end with the FB-1..8 rules, the L1 Inline Resolution Rule, and the Question Suppression Ladder turned on by default.
/dr-compliance
Pipeline
Adaptive post-QA hardening with type-specific checklists
/dr-continue
Utility
Deprecated alias for /dr-next
/dr-design
Pipeline
Explore architectural and design decisions for complex features
/dr-do
Pipeline
TDD implementation with gap discovery — auto-spawns researcher on unknowns
/dr-doctor
Maintenance
Diagnose and migrate operational files to thin-index schema
/dr-dream
Manage
Knowledge base maintenance, organization, and consolidation
/dr-edit
Content
Editorial review with fact-checking and AI pattern removal
/dr-help
Utility
Show the complete Datarim command reference
/dr-init
Pipeline
Initialize a new task, resume from backlog, or scaffold a new project
/dr-next
Utility
Resume work on current task from last checkpoint
/dr-optimize
Manage
Audit and optimize the Datarim framework
/dr-orchestrate
Plugin
Tmux-based self-driving Datarim pipeline runner — Phase 2 (Subagent Inference, autonomy L2)
/dr-plan
Pipeline
Create a detailed implementation plan with security analysis
/dr-plugin
Management
Manage opt-in plugins: list, enable, disable, sync, doctor
/dr-prd
Pipeline
Generate PRD with structured research phase (Phase 1.3) for L2+ tasks
/dr-publish
Content
Format and publish approved content to target platforms
/dr-qa
Pipeline
Multi-layer quality verification across PRD, design, plan, and code
/dr-status
Utility
Check current task status, progress, and backlog summary
/dr-verify
Pipeline
Standalone tri-layer self-verification: deterministic floor + cross-model peer-review (zero-flag UX, 6-step provider chain) + native runtime dispatch
/dr-write
Content
Create written content with structured writing workflow
/factcheck
Auto
Fact-check a file before publication
/humanize
Auto
Remove AI writing patterns from text
55 Skills
Reusable capabilities that agents draw on: quality standards, testing patterns, security checks, infrastructure automation, content writing, fact-checking, and more.
AI Quality
Core
Five pillars of AI-assisted development — decomposition, TDD, architecture-first, focused work, context. Method size limits, DoD, stubbing.
Autonomous Mode
Core
Question Suppression Ladder + L1 Inline Resolution Rule + Hard-gated Action Boundary. Activated via DATARIM_AUTO_MODE=1 + .auto-mode-active marker.
Brainstorming
Task
MUST use this before any creative work — features, components, functionality, behavior changes. Explores user intent and design before implementation.
Compliance
Quality
Post-QA hardening — detects task type (code, docs, research, legal, content, infra) and applies the matching verification checklist before archiving.
Consilium
Core
Assemble a panel of Datarim agents for multi-perspective analysis of decisions. Use for /dr-design stage (L3-4) or critical decisions in /dr-plan.
Coworker Context
Reference
Canonical Datarim conventions reference for external LLMs invoked via the coworker delegation profile. Stage Header, YAML byte-exact, append-log Q&A, expectations checklist, snapshot frontmatter, PRD↔archive mirror, Diátaxis taxonomy, history-agnostic gate, Supreme Directive.
CTA Format
Core
Canonical CTA "Next Step" block format for every /dr-* command and pipeline agent. Single source of truth — load when generating slash-command output.
Datarim Doctor
Maintenance
Schema spec for thin-index operational files: canonical regex, YAML frontmatter contract, 6-pass migration semantics (incl. archive-section enforcement), data-loss safety contract. Loaded on demand by /dr-doctor and /dr-init self-heal.
Datarim System
Core
Core Datarim rules. Load this entry first, then only the fragment needed for paths, storage, numbering, backlog, routing, or archive behavior.
Diátaxis Docs Taxonomy
Reference
Mandate for documentation taxonomy across Datarim-managed repos and product sites: four orthogonal categories (tutorials, how-to, reference, explanation), closed mapping table, exemption list, anti-pattern definitions. Loaded by /dr-init, /dr-optimize audit, /dr-archive surface verification.
Discovery
Core
Structured requirements discovery through focused one-question-at-a-time interviews with proposed answers. Use in /dr-prd stage or before /dr-init.
Dispatching Parallel Agents
Task
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
DR-Continue Snapshot Replay
Reference
Deprecated alias for DR-Next Snapshot Replay.
Dr Init Id Collision Window
Maintenance
Datarim skill dr-init-id-collision-window — see SKILL.md for the canonical contract.
DR-Next Snapshot Replay
Core
Consumer contract for stage snapshots — /dr-next and /dr-orchestrate read datarim/snapshots/{TASK-ID}.snapshot.md first, emit replay-prompt with CTA + bilingual autonomy reminder + done before: body.
Dream
Core
Knowledge base maintenance — organize, deduplicate, cross-reference, and consolidate the datarim/ directory. Flags contradictions, archives stale content.
Evolution
Core
Rules for proposing and applying framework improvements. Covers growth (new components) and maintenance (pruning, merging). Human approval required.
Executing Plans
Task
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Expectations Checklist
Reference
Operator wishlist artefact in plain markdown — wish_id slug, status history, current status, override semantics. Written at the requirements step, verified at the quality-review and hardening steps.
Factcheck
Content
Fact-check articles and posts before publication. Extracts claims, verifies against sources, improves text while preserving style.
File-Sync Configuration
Tech
Pre-flight checklist + ignore patterns for file-sync (Syncthing/rclone/rsync/Dropbox/iCloud) — protects git working trees, virtualenvs, and build artifacts.
Finishing A Development Branch
Task
Use when implementation is complete and all tests pass. Decides how to integrate the work via merge, PR, or cleanup with structured options.
Frontend UI
Quality
Frontend UI checklist — CSS specificity, dark/light themes, visual testing, mobile responsiveness, i18n parity. Apply when editing HTML/CSS.
Health Controller Stub Detector
Quality
Surface hard-coded stub literals (pending-integration, not-implemented, stub) in health/status controllers at /dr-do, before /dr-qa wish gating.
Human Summary
Core
Plain-language operator-facing recap (4 fixed sub-sections, 150–400 words, no jargon, no tables) emitted at the end of /dr-qa, /dr-compliance, and /dr-archive. Anglicism banlist + universal-term whitelist + per-paragraph escape hatch + severity ladder (info / warn / block).
Humanize
Content
Remove AI writing patterns and formatting artifacts from text. Preserves author voice. Use for articles, posts, content that must not look AI-generated.
Infrastructure Automation
Tech
SSH batch execution, ping matrices, health checks for Arcana servers. Use when performing infrastructure operations across multiple servers.
Init-task Persistence
Reference
Verbatim operator brief artefact contract — frontmatter + append-log + Q&A round-trip auto-append + mandatory read by every pipeline command. Source of truth for operator intent across the task lifecycle.
Network Exposure Baseline
Quality
Allowlist/blocklist for network bind targets (compose ports, redis bind, postgres listen_addresses, systemd ListenStream); load before any port change.
Performance
Quality
Optimization patterns (lazy loading, caching, batching), database and frontend performance. Use when designing or reviewing for performance.
Playwright Browser QA
Task
Browser-based frontend quality check — resolution chain across CLI, MCP, and operator-specified browser; default headless mode, optional visible mode, hard-fail strict visible mode.
Post Deploy Env Diff
Quality
Pre-archive gate diffing the on-host env file against the repo template when a deploy changed defaults — catches «prod on stale .env».
Project Init
Core
Project scaffolding — creates CLAUDE.md, docs/, datarim/ structure for new or existing projects. Loaded by /dr-init when project intent is detected.
Publishing
Content
Technical rules for publishing content to social media and websites — platform limits, formatting, API patterns, OG tags, multi-platform workflow.
Receiving Code Review
Task
Use when receiving review feedback before implementing suggestions. Requires technical verification, not performative agreement or blind implementation.
Reflecting
Core
Review-phase workflow — lessons learned, evolution proposals (Class A/B gate), health-metrics check. Invoked by /dr-archive Step 0.5.
Release Verify
Quality
Consumer-side recipe for verifying Datarim releases — sha256 → cosign verify-blob → gh attestation verify. Load on install/update from GitHub Release.
Requesting Code Review
Task
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Research Workflow
Core
Structured external context research — 10-point full checklist (L3-L4), 5-point lite mode (L2), gap discovery protocol for unknowns during implementation.
Security
Quality
Authentication, authorization, input validation, data protection, dependency safety. Use for security review or when handling secrets and user data.
Security Baseline
Quality
Canonical S1–S9 security rule reference cited from CLAUDE.md § Security Mandate. Load for plan/qa/compliance/do touching shipped artifacts.
Self Verification
Quality
Orchestrator for runtime-aware self-verification (manual /dr-verify). Tri-layer: deterministic shell, peer-review, runtime dispatch.
Stage Snapshot Writer
Core
Producer contract for per-task stage snapshots — final operator-visible /dr-* response persisted to datarim/snapshots/{TASK-ID}.snapshot.md with overwrite semantics. Single producer touchpoint via cta-format.md.
Structured Outputs Integration Gate
Quality
Demands schema-unit + wrapper-path tests when API-side structured-output validation is added on top of an existing post-processing pipeline.
Subagent Driven Development
Task
Use when executing implementation plans with independent tasks in the current session
Systematic Debugging
Quality
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Tech Stack
Tech
Tech stack selection by project type (static, API, full-stack, etc.). Use when creating a new project, service, or module or when choosing technologies.
Testing
Quality
Testing pyramid, frameworks (Vitest, Playwright, bats), mocking rules, Live Smoke-Test Gate for raw SQL. Use when writing or reviewing tests.
Using Git Worktrees
Task
Use when starting feature work that needs isolation or before executing plans. Ensures an isolated workspace via native tools or git worktree fallback.
Utilities
Tech
Native shell recipes for common operations. Load this entry first, then only the fragment needed for the specific utility category.
V-AC Axis Split
Reference
Pattern guidance — when a verification-AC group mixes deterministic axis (rule match) and statistical axis (rate threshold over a window), split upfront into two groups.
Verification Before Completion
Quality
Use before claiming work complete, fixed, or passing — and before committing or opening PRs. Run verification commands and confirm output first.
Visual Maps
Tech
Visual index for Datarim maps. Load this entry first, then only the diagram fragment needed for routing, stage flow, or dependency orientation.
Writing
Content
Content creation workflow — research, outlining, drafting, editing, fact-checking, publication prep. Loaded by writer and editor agents.
Writing Plans
Task
Use when you have a spec or requirements for a multi-step task, before touching code
Key Capabilities
Backlog System
Two-file task management: active backlog + archive. Priority levels, complexity estimates, source tracking. Works for solo developers and teams.
Consilium
Multi-agent panel discussions for critical decisions. Assemble a custom panel of agents to debate architecture, security, or strategy — then synthesize a recommendation.
Knowledge Maintenance
/dr-dream organizes your knowledge base: cross-references, deduplication, contradiction detection, stale content archival. Keeps your project documentation healthy.