open-gsd

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

Archive accumulated phase directories from completed milestones

Archive completed milestone and prepare for next version

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

Systematic debugging with persistent state across context resets

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

Diagnose planning directory health and optionally repair issues

File a phase artifact into MemPalace; mirror decision facts into its temporal KG

Orchestrate GSD (Git Ship Done) projects programmatically via headless CLI. Use when an agent needs to create milestones from specs, execute dev workflows, monitor progress, check status, or control execution (pause/stop/skip/steer). Triggers on "run gsd",…

Build software products autonomously via GSD headless mode. Handles the full lifecycle: write a spec, launch a build, poll for completion, handle blockers, track costs, and verify the result. Use when asked to "build something", "create a project", "run gsd",…

Expert guidance for creating, writing, building, and refining GSD skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

Package findings from a completed spike into a durable project-local skill that auto-loads on future similar work. Reads the latest `.gsd/workflows/spikes/` dir, interviews the user on what's reusable, then writes `.agents/skills/<name>/SKILL.md`. Use when…

Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis.

Break a plan or milestone brief into independently-grabbable vertical slices (tracer bullets), written to `M###-ROADMAP.md` by default (GitHub issues only on explicit confirmation). Prefers many thin slices over few thick ones and marks dependency order. Use…

Post-mortem a failed GSD auto-mode run. Traces symptom to root cause via `.gsd/` activity, journal, metrics, and lock artifacts, producing a filing-ready bug report with file:line refs and a fix suggestion. Use when asked to "forensics", "post-mortem", "why…

Relentless sequential interview that stress-tests a plan or design until every decision branch is resolved. Use when the user wants to "grill me", "stress-test the plan", "interrogate my design", "resolve the decision tree", or whenever a plan feels…

Create or update a native recurring task that repeatedly runs one-pass gsd-loop builder or reviewer work. Use when asked to keep the build or review queue running, schedule gsd-loop, or automate repeated passes.

Chart or advance one interactive discovery map, shape it into one or more delivery slices, then hand those slices to gsd-loop-spec. Never runs unattended or writes product code.

Turn a rough idea or cleared discovery map into one or more contract-grade GitHub issues for the gsd-loop queue. Interactive only; never run unattended.

Chart or advance one interactive discovery map, shape it into one or more delivery slices, then hand those slices to gsd-loop-spec. Never runs unattended or writes product code.

Turn a rough idea or cleared discovery map into one or more contract-grade GitHub issues for the gsd-loop queue. Interactive only; never run unattended.

Build the oldest safe gsd:ready GitHub issue or repair one gsd:rework PR. Use when asked to run the gsd-loop builder, work the ready queue, or fix rework. Each invocation completes exactly one pass, then stops.

Audit one open PR against its linked issue contract and required CI, then post a gsd-loop verdict and labels. Use when asked to run the reviewer or audit the PR queue. Never merge or push; each invocation completes one pass.

Build the oldest safe gsd:ready GitHub issue or repair one gsd:rework PR. Use when asked to run the gsd-loop builder, work the ready queue, or fix rework. Each invocation completes exactly one pass, then stops.

Open GSD native browser automation for AI agents. Use gsd-browser when the user needs real Chrome/Chromium control: navigate pages, inspect localhost, click, type, fill forms, take screenshots, capture stable snapshot refs, run assertions and waits, extract…

Open GSD native browser automation for AI agents. Use gsd-browser when the user needs real Chrome/Chromium control: navigate pages, inspect localhost, click, type, fill forms, take screenshots, capture stable snapshot refs, run assertions and waits, extract…

Open GSD native browser automation for AI agents. Use gsd-browser when the user needs real Chrome/Chromium control: navigate pages, inspect localhost, click, type, fill forms, take screenshots, capture stable snapshot refs, run assertions and waits, extract…

Auto-build and continuously update the project knowledge graph (.gsd-graph/) for brownfield onboarding and ongoing work — enable, sync, status, ask

Run a project's Node tests without leaking orphaned processes onto this machine. Use whenever you would run `node --test`, `npm test`, or `npm run test` — call `gsd-test run` instead of spawning the test process locally. Also use when a run comes back reaped,…