gsd:help
25Command Claude Code
Show available GSD commands and usage guide.
Command Claude Code
Show available GSD commands and usage guide.
Command Claude Code
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents.
Command Claude Code
Start a new milestone cycle — update PROJECT.md and route to requirements.
Command Claude Code
Initialize a new project with deep context gathering and PROJECT.md.
Command Claude Code
Create context handoff when pausing work mid-phase.
Command Claude Code
Create detailed phase plan (PLAN.md) with verification loop.
Command Claude Code
Check progress, advance workflow, or dispatch freeform intent — the unified GSD situational command.
Command Claude Code
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
Command Claude Code
Resume work from previous session with full context restoration.
Command Claude Code
Configure GSD workflow toggles and model profile.
Command Claude Code
Update GSD to latest version with changelog display.
Command Claude Code
Retroactively audit and fill Nyquist validation gaps for a completed phase.
Command Claude Code
Validate built features through conversational UAT.
Skill Claude Code
Produce a structured, end-to-end linear walkthrough of an unfamiliar codebase. Use when onboarding to a new repository, understanding how a system works from entry points through execution paths, or generating navigable codebase documentation. Spawns parallel subagents for discovery, tracing, validation, and synthesis…
Skill Claude Code
Enforces memory-mapped file I/O for large file processing in Python. Use when reading, searching, or processing files larger than 100MB, or when performing delimiter/boundary searches without loading the entire file into RAM. Rejects pathlib.readbytes(), readtext(), and f.read() on files of unknown or large size.
Cursor rule Cursor
Typing policy, SOLID/DRY, and non-negotiable design quality for this repo.
Plugin Claude Code
Bundles 1 skill · 50 tokens together
Guide Claude agents through using the skilllint CLI to validate, fix, and understand linting violations in Claude Code plugins, skills, agents, and commands.
Agent Claude Code
Researches a single gray area decision and returns a structured comparison table with rationale. Spawned by discuss-phase advisor mode.
Agent Claude Code
Researches a chosen AI framework's official docs to produce implementation-ready guidance — best practices, syntax, core patterns, and pitfalls distilled for the specific use case. Writes the Framework Quick Reference and Implementation Guidance sections of AI-SPEC.md. Spawned by /gsd:ai-integration-phase orchestrator.
Agent Claude Code
Deeply analyzes codebase for a phase and returns structured assumptions with evidence. Spawned by discuss-phase assumptions mode.
Agent Claude Code
Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd:code-review --fix.
Agent Claude Code
Reviews source files for bugs, security issues, and code quality problems. Produces structured REVIEW.md with severity-classified findings. Spawned by /gsd:code-review.
Agent Claude Code
Manages multi-cycle /gsd:debug checkpoint and continuation loop in isolated context. Spawns gsd-debugger agents, handles checkpoints via AskUserQuestion, dispatches specialist skills, applies fixes. Returns compact summary to main context. Spawned by /gsd:debug command.
Agent Claude Code
Classifies a single planning document as ADR, PRD, SPEC, DOC, or UNKNOWN. Extracts title, scope summary, and cross-references. Spawned in parallel by /gsd:ingest-docs. Writes a JSON classification file and returns a one-line confirmation.
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: