Features
Everything you need to run AI-assisted projects at any scale
9-Stage Pipeline
Not every task goes through all stages. A simple fix: init → do → reflect → archive. A major project: all 9 stages with multi-agent review.
Analyze task, determine complexity (L1-L4), create tracking
Product requirements with discovery interview and alternatives
Detailed implementation plan with strategist review
Architecture exploration for complex features (L3-4)
TDD implementation — test first, code second
4-layer quality check: PRD, design, plan, output
Adaptive post-QA hardening by task type
Lessons learned, evolution proposals for the framework
Complete documentation, update backlog, close task
15 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.
Lead PM — backlog, detailed design, implementation plans
System integrity, scalability, architectural patterns
TDD implementation, code quality, project patterns
QA & security lead, code reviews, Definition of Done
Post-QA hardening, adaptive checklists by task type
Refactoring for clarity and consistency
Value/Risk/Cost evaluation, constructive skepticism
Articles, docs, research papers, structured text
Editorial review, fact verification, AI pattern removal
Build-ship-run pipeline, CI/CD, containerization
Reliability, observability, incident response
Threat modeling, vulnerability assessment, compliance
Research and generate new skills, agents, commands
Framework audit — prune, merge, consolidate
Knowledge base maintenance, indexing, cross-references
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.
18 Skills
Reusable capabilities that agents draw on: quality standards, testing patterns, security checks, SEO, content writing, fact-checking, and more.