gsd-core

Build, query, and inspect the project knowledge graph in .planning/graphs/

Post-mortem investigation for failed GSD workflows — diagnoses what went wrong.

Execute a trivial task inline — no subagents, no planning overhead

Extract decisions, lessons, patterns, and surprises from completed phase artifacts

Socratic ideation and idea routing — think through ideas before committing to plans

Execute all plans in a phase with wave-based parallelization

Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.

Generate or update project documentation verified against the codebase

Gather phase context through adaptive questioning before planning.

Systematic debugging with persistent state across context resets

Configure GSD settings — workflow toggles, advanced knobs, integrations, and model profile

Archive completed milestone and prepare for next version

Review source files changed during a phase for bugs, security issues, and code quality problems

Archive accumulated phase directories from completed milestones

Capture ideas, tasks, notes, and seeds to their destination

Run all remaining phases autonomously — discuss→plan→execute per phase

Cross-phase audit of all outstanding UAT and verification items

Audit milestone completion against original intent before archiving

Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit

Generate an AI-SPEC.md design contract for phases that involve building AI systems.

Generate tests for a completed phase based on UAT criteria and implementation