2d3027767b
* test(#3426): add RED test for Codex Windows hooks .cmd shim requirement Drive buildCodexHookWindowsShimIR (typed IR) + ensureCodexHooksJsonSessionStart integration against mocked win32 platform. Counter-tests confirm darwin/linux paths remain unchanged. NOTE: Windows wall-clock verification depends on Docker matrix Windows runners. Local test exercises the generator IR shape only. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(#3426): Codex Windows hooks use .cmd shim to avoid bash.exe POSIX-exec failure Root cause: Codex on Windows runs hook commands from PowerShell/cmd. The previous hooks.json command format was `"node.exe" "script.js"`. Codex's hook-dispatch shell (Git Bash / MSYS) tried to POSIX-exec node.exe (a Windows PE binary) via execvp(), which fails with ENOEXEC — reported as `bash.exe: cannot execute binary file`. Fix: `ensureCodexHooksJsonSessionStart` now calls `buildCodexHookWindowsShimIR` on win32 to write a .cmd shim alongside the .js hook file. cmd.exe executes .cmd files natively via CreateProcess, bypassing the POSIX exec layer entirely. Non-Windows paths (darwin, linux) are unchanged: they continue to use the node-runner command. Also adds `gsd-check-update.cmd` to the codex-hooks-json managed-basename set so reconcileCodexHooksJsonSessionStart correctly replaces stale node-runner entries on reinstall. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * chore(3426): update changeset to reference PR #3768 * fix(3426): fail-loud on Codex Windows shim-write failure instead of silently restoring broken command Replace the silent fallback to `projectManagedHookCommand` (the old `node.exe script.js` form) with an explicit warn-and-skip path. When `atomicWriteFileSync` fails to write the `.cmd` shim, the previous code silently called `reconcileCodexHooksJsonSessionStart` with the legacy node-runner command. That command triggers the exact `bash.exe: cannot execute binary file` POSIX-exec failure that #3426 exists to fix — so a successful-looking install was secretly restoring the original bug. New behaviour: - Emit `console.warn` with the failure reason and a remediation hint, matching the `${yellow}⚠${reset} Skipped …` idiom used at line 9098. - Return `{ changed: false, wrote: false }` to skip registration for this runtime entirely, so the outer caller can surface "NOT installed" instead of "installed (but broken)". Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * test(3426): typed-IR assertions on .cmd shim eol/quoting/passthrough + IR extension Extend `buildCodexHookWindowsShimIR` to expose two new typed fields on the returned IR object (CONTRIBUTING.md L558-L565 IR-first discipline): eol: { cmd: '\r\n' } — CRLF is canonical for cmd.exe .cmd files passthroughArgs: true — shim forwards all args via %* Add a new describe block (Step 2b) with three IR-level assertions: 1. `eol.cmd === '\r\n'` — prevents silent EOL regression that could break parsing on Windows versions that require CRLF. 2. `invocation.target` is the raw unquoted path (no shell-metachar leakage) — quoting happens only at render time. 3. `passthroughArgs === true` — the %* forwarding contract is explicitly typed so regressions fail before the text is rendered. All assertions operate on the typed IR returned by the generator, NOT on the rendered `.cmd` file content — text-matching is the anti-pattern CONTRIBUTING.md L522-582 prohibits. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * test(3426): fix Windows CI failures — update hook-command filter patterns Four test files filtered for managed hooks in hooks.json using the literal string `gsd-check-update.js`. On Windows the PR-introduced .cmd shim changes the hooks.json command to `"path/gsd-check-update.cmd"` (no node prefix, .cmd extension), so those filters matched 0 entries and 24 Windows subtests failed. Fixes: - bug-2760-codex-install-defensive.test.cjs (7 filters): change `/gsd-check-update\.js/` → `/gsd-check-update/` to match both .js (POSIX) and .cmd (Windows) commands. - bug-3357-codex-legacy-hooks-json-migration.test.cjs (3 filters): same `.js` → no-extension change. - bug-3427-3433-codex-install-shape.test.cjs (2 filters): same fix; add explanatory comment to uninstall assertion. - codex-config.test.cjs (9 filters + 1 exact-command assertion): bulk-replace all `hooksJsonCommands.filter(cmd => cmd.includes('gsd-check-update.js'))` with `gsd-check-update`; make the `fresh CODEX_HOME` test platform- aware — on win32 assert `.cmd` shim path, on POSIX assert the existing `"runner" "script.js"` form (#3017). All four suites pass locally (macOS / darwin). Windows subtests verified against the Windows CI failure log patterns. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(3426): address pr-review-toolkit + codex review findings - fix(uninstall): add gsd-check-update.cmd to gsdHooks cleanup list so the .cmd shim is removed from disk on Windows uninstall (was left as orphan artifact — silent failure post-uninstall) - test(3426): add uninstall test asserting gsd-check-update.cmd is deleted from hooks dir after `uninstall(true, 'codex')` (no coverage existed) - fix(comment): correct JSDoc on buildCodexHookWindowsShimIR — shim content is three-line @ECHO OFF/@SETLOCAL/@runner snippet, not bare `@node "script.js" %*` as the old comment claimed - fix(comment): update stale assertion message in codex-config.test.cjs L1457 — said "config.toml references it" but the hook is in hooks.json Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
GET SHIT DONE
English · Português · 简体中文 · 日本語 · 한국어
A light-weight meta-prompting, context engineering, and spec-driven development system for Claude Code, OpenCode, Gemini CLI, Kilo, Codex, Copilot, Cursor, Windsurf, and more.
Solves context rot — the quality degradation that happens as your AI fills its context window.
npx get-shit-done-cc@latest
Works on Mac, Windows, and Linux.
"If you know clearly what you want, this WILL build it for you. No bs."
"I've done SpecKit, OpenSpec and Taskmaster — this has produced the best results for me."
"By far the most powerful addition to my Claude Code. Nothing over-engineered. Literally just gets shit done."
Trusted by engineers at Amazon, Google, Shopify, and Webflow.
Important
Returning to GSD?
Run
/gsd-map-codebaseto re-index your codebase, then/gsd-new-projectto rebuild GSD's planning context. Your code is fine — GSD just needs its context rebuilt. See the CHANGELOG for what's new.
Why I Built This
I'm a solo developer. I don't write code — Claude Code does.
Other spec-driven tools exist, but they're all built for 50-person engineering orgs — sprint ceremonies, story points, stakeholder syncs, Jira workflows. I'm not that. I'm a creative person trying to build great things consistently.
So I built GSD. The complexity is in the system, not in your workflow. Behind the scenes: context engineering, XML prompt formatting, subagent orchestration, state management. What you see: a few commands that just work.
The system gives Claude everything it needs to do the work and verify it. I trust the workflow. It just does a good job.
— TÂCHES
How It Works
The loop is six commands. Each one does exactly one thing.
1. Initialize
/gsd-new-project
Questions → research → requirements → roadmap. You approve it, then you're ready to build.
Already have code? Run
/gsd-map-codebasefirst. It analyzes your stack, architecture, and conventions so/gsd-new-projectasks the right questions.
2. Discuss
/gsd-discuss-phase 1
Your roadmap has a sentence per phase. That's not enough to build it the way you imagine it. Discuss captures your decisions before anything gets planned: layouts, API shapes, error handling, data structures — whatever gray areas exist for this specific phase.
The output feeds directly into research and planning. Skip it, get reasonable defaults. Use it, get your vision.
3. Plan
/gsd-plan-phase 1
Research → plan → verify, in a loop until the plans pass. Each plan is small enough to execute in a fresh context window.
4. Execute
/gsd-execute-phase 1
Plans run in parallel waves. Each executor gets a fresh 200k-token context. Each task gets its own atomic commit. Walk away, come back to completed work with a clean git history.
Your main context window stays at 30–40%. The work happens in the subagents.
5. Verify
/gsd-verify-work 1
Walk through what was built. Anything broken gets a diagnosed fix plan — ready for immediate re-execution. You don't debug manually; you just run execute again.
6. Repeat → Ship
/gsd-ship 1
/gsd-complete-milestone
/gsd-new-milestone
Loop discuss → plan → execute → verify → ship until the milestone is done. Then archive, tag, and start the next one fresh.
Getting Started
npx get-shit-done-cc@latest
The installer prompts for your runtime (Claude Code, OpenCode, Gemini CLI, Kilo, Codex, Copilot, Cursor, Windsurf, and more) and whether to install globally or locally.
claude --dangerously-skip-permissions
GSD is built for frictionless automation. Skip-permissions is how it's intended to run.
Install only the skills you need with --profile=core (six core-loop skills), --profile=standard (core + phase management), or the default full install. Profiles compose: --profile=core,audit. --minimal is an alias for --profile=core. See docs/USER-GUIDE.md for the full walkthrough, non-interactive install flags for all 15 runtimes, and permissions configuration. See ADR-0011 for the profile model and runtime surface control.
Current release highlights are in docs/RELEASE-v1.42.1.md: package legitimacy checks, safer installer migrations, runtime surface control, custom ship PR sections, reviewer defaults, fallow structural review, and quota-aware execution recovery.
Commands
The main loop:
| Command | What it does |
|---|---|
/gsd-new-project |
Questions → research → requirements → roadmap |
/gsd-discuss-phase [N] |
Capture implementation decisions before planning |
/gsd-plan-phase [N] |
Research + plan + verify |
/gsd-execute-phase <N> |
Execute plans in parallel waves |
/gsd-verify-work [N] |
Manual acceptance testing |
/gsd-ship [N] |
Create PR from verified phase work |
/gsd-progress --next |
Auto-detect and run the next step |
/gsd-complete-milestone |
Archive milestone and tag release |
/gsd-new-milestone |
Start next version |
/gsd:surface |
Enable/disable skill clusters at runtime without reinstall |
For ad-hoc tasks, autonomous mode, codebase analysis, forensics, and the full command surface — see docs/COMMANDS.md.
Why It Works
Three things most AI-coding setups get wrong:
1. Context bloat. As a session grows, quality degrades. GSD keeps your main context clean by doing the heavy work in fresh subagent contexts. Researchers, planners, and executors each start fresh with exactly what they need.
2. No shared memory. GSD maintains structured artifacts that survive session boundaries: PROJECT.md (vision), REQUIREMENTS.md (scope), ROADMAP.md (where you're going), STATE.md (current position and decisions), CONTEXT.md (per-phase implementation decisions). Every new session loads these and knows exactly where things stand.
3. No verification. Code that "runs" isn't code that "works." GSD's verify step walks you through what was built, diagnoses failures with dedicated debug agents, and generates fix plans before you declare a phase done.
See docs/ARCHITECTURE.md for how the multi-agent orchestration and context engineering work in detail.
Configuration
Settings live in .planning/config.json. Configure during /gsd-new-project or update with /gsd-settings.
Key dials:
| Setting | What it controls |
|---|---|
mode |
interactive (confirm each step) or yolo (auto-approve) |
| Model profiles | quality / balanced / budget — controls which model each agent uses |
workflow.research / plan_check / verifier |
Toggle the quality agents that add tokens and time |
parallelization.enabled |
Run independent plans simultaneously |
Optional structural review: set code_quality.fallow.enabled to true to add a fallow pre-pass to /gsd-code-review. GSD writes .planning/phases/<phase>/FALLOW.json and surfaces a Structural Findings (fallow) section in REVIEW.md. Install with npm install -D fallow@^2.70.0 (or system-wide via cargo install fallow; note that the Rust binary's JSON schema must match the documented v2.70+ contract — older versions may produce silent zero-finding output).
Package legitimacy checks are built into the research, planning, and execution path: recommended dependencies get audited, unverified packages require a human checkpoint, and failed installs stop instead of trying similarly named alternatives.
For the full configuration reference — all settings, git branching strategies, per-runtime model overrides, workstream config inheritance, agent skills injection — see docs/CONFIGURATION.md.
Documentation
| Doc | What's in it |
|---|---|
| User Guide | End-to-end walkthrough, install options, all runtime flags, configuration reference |
| Commands | Every command with flags and examples |
| Configuration | Full config schema, model profiles, git branching |
| Architecture | How the multi-agent orchestration works |
| CLI Tools | gsd-sdk query and programmatic SDK dispatch seams |
| Features | Complete feature index |
| Changelog | What changed in each release |
Troubleshooting
Commands not showing up? Restart your runtime after install. GSD installs to ~/.claude/skills/gsd-*/ (Claude Code), ~/.codex/skills/gsd-*/ (Codex), or the equivalent for your runtime.
Codex users — minimum supported CLI version is 0.130.0. Codex CLI 0.130.0 (release notes) removed extra-skill-roots discovery via openai/codex#21485; from that version onward Codex discovers skills from standard roots (including ~/.codex/skills/<name>/SKILL.md). GSD installs there directly. Earlier Codex CLI versions may still discover additional roots, which can surface duplicate gsd-* entries (one from extra-roots discovery, one from ~/.codex/skills/); restart Codex after install and either upgrade or accept the duplicate listing.
Something broken? Re-run the installer — it's idempotent:
npx get-shit-done-cc@latest
Containers or Docker? Set CLAUDE_CONFIG_DIR before installing to avoid tilde-expansion issues:
CLAUDE_CONFIG_DIR=/home/youruser/.claude npx get-shit-done-cc --global
Full troubleshooting and uninstall instructions in docs/USER-GUIDE.md.
Community
| Project | Platform |
|---|---|
| gsd-opencode | Original OpenCode port |
| Discord | Community support |
Star History
License
MIT License. See LICENSE for details.
Claude Code is powerful. GSD makes it reliable.