Command Claude Code
Add an idea to the backlog parking lot (999.x numbering).
Verified knowledge base for AI agents via MCP — certified facts with source references, confidence scores, and SHA256 integrity hashes
This repository also configures its own agents. See what swiss-truth-mcp tells them →
Command Claude Code
Add an idea to the backlog parking lot (999.x numbering).
Command Claude Code
Add phase to end of current milestone in roadmap.
Command Claude Code
Generate tests for a completed phase based on UAT criteria and implementation.
Command Claude Code
Capture idea or task as todo from current conversation context.
Command Claude Code
Generate AI design contract (AI-SPEC.md) for phases that involve building AI systems — framework selection, implementation guidance from official docs, and evaluation strategy.
Command Claude Code
Analyze phase dependencies and suggest Depends on entries for ROADMAP.md.
Command Claude Code
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit.
Command Claude Code
Audit milestone completion against original intent before archiving.
Command Claude Code
Cross-phase audit of all outstanding UAT and verification items.
Command Claude Code
Run all remaining phases autonomously — discuss→plan→execute per phase.
Command Claude Code
List pending todos and select one to work on.
Command Claude Code
Archive accumulated phase directories from completed milestones.
Command Claude Code
Auto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary.
Command Claude Code
Review source files changed during a phase for bugs, security issues, and code quality problems.
Command Claude Code
Archive completed milestone and prepare for next version.
Command Claude Code
Systematic debugging with persistent state across context resets.
Command Claude Code
Gather phase context through adaptive questioning before planning. Use --all to skip area selection and discuss all gray areas interactively. Use --auto to skip interactive questions (Claude picks recommended defaults). Use --chain for interactive discuss followed by automatic plan+execute. Use --power for bulk…
Command Claude Code
Route freeform text to the right GSD command automatically.
Command Claude Code
Generate or update project documentation verified against the codebase.
Command Claude Code
Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan.
Command Claude Code
Execute all plans in a phase with wave-based parallelization.
Command Claude Code
Socratic ideation and idea routing — think through ideas before committing to plans.
Command Claude Code
Extract decisions, lessons, patterns, and surprises from completed phase artifacts.
Command Claude Code
Execute a trivial task inline — no subagents, no planning overhead.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: