open-gsd

Create detailed phase plan (PLAN.md) with verification loop

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

Cross-AI plan convergence - replan until review concerns are resolved.

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

Start a new milestone cycle — update PROJECT.md and route to requirements

Toggle which skills are surfaced — apply a profile, list, or disable a cluster without reinstall

project lifecycle | milestones audits summary

Guide existing codebase onboarding through mapping, doc ingest, and planning setup

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", "create milestone", "execute project", "check gsd status", "orchestrate development", "run headless workflow", or building orchestrators that coordinate multiple GSD workers.

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", "check build status", or any task that requires autonomous software development via subprocess.

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 asked to "wrap up the spike", "package this as a skill", "make this reusable", "turn findings into a skill", or at the synthesize phase of `/gsd start spike`.

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 when asked to "break this into slices", "decompose the plan", "vertical slices", "break into issues", or when a plan needs task-level decomposition.

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 did auto-mode fail", "trace the stuck loop", "debug the crash", after `/gsd forensics`, or when a session ended in an unexpected terminal state. Reads artifacts only — re-runs nothing.

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 hand-wavy, under-specified, or carries hidden coupling that planning phases must surface before execution. Pairs with the discuss phase and blocks execution until alignment is reached.

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 structured data, compare visual diffs, inspect console/network behavior, mock or block requests, emulate devices, save auth state, record evidence bundles, scan for prompt injection, or share a live browser viewer for human handoff. Good prompts include "inspect this URL", "verify this user flow", "debug this page", "capture evidence", "scrape this table", "show me the browser", "pause/step through this", "login to a site", or "run a visual regression test". Learn more at https://opengsd.net/ and https://github.com/open-gsd/gsd-browser.

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 structured data, compare visual diffs, inspect console/network behavior, mock or block requests, emulate devices, save auth state, record evidence bundles, scan for prompt injection, or share a live browser viewer for human handoff. Good prompts include "inspect this URL", "verify this user flow", "debug this page", "capture evidence", "scrape this table", "show me the browser", "pause/step through this", "login to a site", or "run a visual regression test". Learn more at https://opengsd.net/ and https://github.com/open-gsd/gsd-browser.

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 structured data, compare visual diffs, inspect console/network behavior, mock or block requests, emulate devices, save auth state, record evidence bundles, or share a live browser viewer for human handoff. Good prompts include "inspect this URL", "verify this user flow", "debug this page", "capture evidence", "scrape this table", "show me the browser", "pause/step through this", "login to a site", or "run a visual regression test". Learn more at https://opengsd.net/ and https://github.com/open-gsd/gsd-browser.

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, or when a previous local test run left hung `node` processes behind.