ef951098a6
* chore(3686): add release-tarball lifecycle smoke to install-smoke workflow Closes #3686. Adds a non-interactive lifecycle smoke that runs against the installed tarball (not the working tree). Catches the two recent release-time bug classes that the working-tree test suite cannot see: * #3684 — symbol mismatches between init.cjs imports and secrets.cjs exports that landed in v1.42.3 (closed/fixed-pending-release). * #3668 — bare `gsd-sdk` invocations in 75 of 78 workflow files with no `command -v gsd-sdk … elif node "$GSD_TOOLS"` fallback (open). Shape: * `scripts/release-tarball-smoke.cjs` — pure CJS module exporting a frozen `SMOKE` enum and a `runSmoke({ tarballPath, installPrefix, expectedVersion, fixtureDir, lifecycleCommands })` function. CLI `--json` mode prints `JSON.stringify(result)` and exits 0 iff `result.code === SMOKE.OK`. Install is `--prefix <tmpdir>` so it does not pollute global node_modules. * `tests/release-tarball-smoke.test.cjs` — 6 tests covering happy path, version mismatch, lifecycle command file resolution, missing-command detection, sdk binary callability, and structural workflow-body checks. Tests assert on the SMOKE enum directly; no `assert.match` on rendered prose, no try/finally in test bodies, no source-grep theater. Uses `before`/`after` to pack+install once across the test file. * `tests/release-tarball-smoke-workflow.test.cjs` — 7 structural assertions on the parsed install-smoke.yml IR (workflow_call trigger preserved, lifecycle step calls release-tarball-smoke.cjs with --json, jq check enforces result.code === "ok", path filter includes the new files, artifact-on-failure step present). * `.github/workflows/install-smoke.yml` — extended (not duplicated). New "Lifecycle smoke" step after the existing version check, on the same matrix. Artifact upload on failure for debugging. Path filter now triggers on changes to the new script + test. Per CONTRIBUTING.md §"Prohibited: Raw Text Matching on Test Outputs" this PR avoids the same anti-pattern that caused PR #3666 to be reverted (PR #3688) — the script returns frozen enum codes, tests assert on the enum, never on stdout strings. Workflow-body checks in Cycle 3 are INFORMATIONAL (count returned, not enforced) on this PR. After #3668's fix lands and the 75 missing fallbacks are added, the lane can be tightened to enforce zero. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(3686): harden release smoke workflow and query scanner * fix(3686): move tarball-smoke test to install suite to fix Windows ETIMEDOUT + coverage OOM Windows (Node 22/24/26, jobs 76565215694/76565215710/76565215812): release-tarball-smoke.test.cjs had no suite marker so run-tests.cjs classified it as 'unit', running it on Windows PR CI. The before() hook calls execFileSync(npm.cmd install -g ...) with a 55 s timeout; on Windows GHA runners this npm global install consistently hits ETIMEDOUT (~62 s observed), causing all 3 Windows lanes to fail. Coverage (job 76565215085): c8 ran test:coverage:unit (unit suite only) with V8 coverage tracking active across child processes. The tarball-smoke test's before() hook spawned npm install subprocesses while c8 held V8 coverage descriptors open, driving the Node heap to 4 GB+ and triggering an OOM abort during report generation (exit code 134, all 5682 tests had already passed). Fix: rename to tests/release-tarball-smoke.install.test.cjs so run-tests.cjs routes it to the 'install' suite. The install suite is already skipped on PR CI by design (test.yml lines 179-181: only runs on main push). The dedicated install-smoke.yml workflow continues to exercise this test on its own matrix. Also update the install-smoke.yml PR path filter and the structural wiring test assertion to match the new filename. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * refactor(test): route tarball-smoke install test through tests/helpers.cjs Replaces direct fs.mkdtempSync and execFileSync calls in tests/release-tarball-smoke.install.test.cjs with createTempDir() and a new runNpm() helper in tests/helpers.cjs. Cleanup is now automatic via the helper. Addresses CodeRabbit Major refactor at https://github.com/gsd-build/get-shit-done/pull/3692#discussion_r3260433892. --------- Co-authored-by: Claude Opus 4.7 (1M context) <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.