ea67479bfb
* fix(3496): include all version patterns in changelog extraction parseChangelog now handles multi-line bullets (continuation lines starting with two or more spaces) where the (#NNNN) PR trailer appears on a continuation line, not the opening dash line. The previous single-line regex silently dropped every such bullet, causing Feature/Enhancement sections to return 0 entries. Also adds an `extract` subcommand to scripts/changeset/cli.cjs: changeset/cli.cjs extract --from VERSION --to VERSION [--changelog FILE] [--json] Extracts releases strictly after --from (exclusive) and up to and including --to (inclusive). Accepts v-prefixed versions. Exits 2 when no releases fall in range, giving /gsd:update a deterministic range-aware helper instead of vague/manual extraction. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * test(3496): use production parseChangelog in markdown-mode assertion Replace raw stdout.includes() in the emits-markdown test with a parseChangelog call on the output so the assertion targets version strings via the production parser rather than a raw substring match. Eliminates the output-grep anti-pattern flagged by test-rigor. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * chore(changeset): add fragment for fix #3796 (issue #3496) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(3496): reject malformed --from/--to semver in extract with structured error `parseSemver` coerced non-numeric components to 0 (e.g. `1.41.x` → `1.41.0`), making range selection silently wrong under typos or version-shape drift. Add a strict N.N.N validation gate before comparison; exit 1 with a JSON error report when either bound fails. Add two regression tests covering alphabetic and dotted-letter inputs. Codex adversarial review finding: high severity (scripts/changeset/cli.cjs:226-244) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(3496): preserve bullets without PR trailer in parseChangelog (pr: null) Previously flushBullet() silently discarded any bullet that lacked a trailing (# NNNN) token. On the real CHANGELOG.md this dropped 7 entries from v1.41.0 alone, so cmdExtract returned incomplete release notes to the /gsd:update confirmation step. Store PR-less bullets as { body, pr: null } instead. Update cmdExtract's textOutput renderer to emit `- body` (no trailer) for null-pr bullets. Add regression tests: - serialize: preserves bullets without trailer as pr:null (not dropped) - cli extract: preserves PR-less and PR bullets together in extracted JSON - cli extract: rejects malformed --from/--to (1.41.x, foo) with exit 1 Codex adversarial review finding: high severity (scripts/changeset/serialize.cjs:64-73) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(3496): wire extract into update.md + reject pre-release in range, fix CHANGELOG parser edge cases BLOCKER fixes: - F1: workflows/update.md show_changes_and_confirm step now invokes `scripts/changeset/cli.cjs extract --from $INSTALLED_VERSION --to $LATEST_VERSION --changelog $CHANGELOG_TMP --json` with explicit exit-2 handling ("no releases in range") and fallback text. The prior prose ("extract entries between versions") was never wired to the binary and silently skipped intermediate versions (#3496). - F2: releases.filter in cmdExtract now rejects any rel.version that does not pass SEMVER_RE before numeric-tuple comparison. parseSemver('1.0.0-rc.1') previously returned [1,0,0] (same as '1.0.0'), causing pre-release entries to corrupt range queries. Architectural choice: skip pre-release + 4-part versions with a stderr warning; full semver §11 pre-release ordering deferred to a consolidation issue (see F8 note below). MAJOR fixes: - F3 (serialize.cjs): releaseMatch regex updated to /^##\s+\[([^\]]+)\](?:\([^)]*\))?\s*(?:-\s*(\S+))?/ so linked-header format `## [1.42.1](url) - 2026-05-15` captures the date correctly. - F4 (serialize.cjs): continuation-line test now checks `!/^\s+-\s/` so ` - nested item` terminates the current bullet instead of folding in. - F5 (cli.cjs): 4-part versions (e.g. 1.0.0.1) fail SEMVER_RE and are skipped by the same guard added for F2. No separate code path needed. - F6 (serialize.cjs): v-prefix stripped from in-file version capture; `## [v1.0.0]` now parses as version "1.0.0". - F7 (serialize.cjs): continuation-line indentation relaxed from /^[ \t]{2}/ to /^\s+/ so 1-space-indented continuations fold correctly (F4's bullet-terminator guard prevents nested bullets from being folded). MINOR fixes: - F9 (cli.cjs): unknown-command path now exits 1 instead of 2 (exit 2 is reserved for "no releases in range" semantic). - F10 (cli.cjs): text-mode exit-2 path now writes "no releases found in range (from=X, to=Y)" to stderr. - F11 (tests): exit-2 test now asserts r.json is present and r.json.releases.length === 0. NOTE — F8 (semver consolidation): this codebase has 5+ distinct semver comparators with divergent pre-release policies; this PR adds a 6th (the SEMVER_RE guard in cmdExtract). A follow-up consolidation issue should be filed to unify all call sites. Out of scope for this PR. Regression tests added for F1–F6: pre-release exclusion, linked-header date parsing, nested-bullet termination, 4-part/v-prefix edge cases, and workflow wiring. All 15 tests pass. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(lint): add allow-test-rule annotation to F1 workflow wiring test The F1 test reads get-shit-done/workflows/update.md (a product markdown file, not CJS source) to assert the extract subcommand invocation was wired. The lint-no-source-grep detector flags any readFileSync-bound variable used with .includes() regardless of file extension; annotate with // allow-test-rule to exempt this legitimate product-content assertion. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * test: apply deterministic barrier to locking-bugs #1927 config-set test The 'both concurrent config-set calls persist their values' test used Promise.all([execAsync(A), execAsync(B)]) without a barrier, which is non-deterministic under Docker load: one subprocess can complete before the other starts (no real contention) or both can race O_EXCL and observe stale fs state (lost write / assertion failure). Mirrors the locking-bugs:180 and :235 redesigns: erect a barrier file, spawn both subprocesses, wait for both to signal readiness via ready files, then drop the barrier simultaneously so both config-set calls genuinely contend on withPlanningLock. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
⚠️ This is the active fork
📢 Read the announcement: why the fork, what changed, what's next →
The original repo at gsd-build/get-shit-done appears compromised or abandoned. The maintainer (TÂCHES) has not been reachable since 2026-04-01. TÂCHES social accounts appear deleted, and a
$GSDtoken associated with the project has been linked publicly to a rug-pull.I have no inside information beyond what is publicly visible. I am stating absence-of-information deliberately — absence of news is not the same as evidence.
What I can confirm
- No contact with the original maintainer since 2026-04-01.
- TÂCHES social accounts appear deleted or unreachable.
- The
$GSDtoken has been linked publicly to a rug-pull.- The repo at
gsd-build/get-shit-donecontinues to exist but I cannot vouch for any changes pushed there from this point forward.What changed
Before After GitHub gsd-build/get-shit-doneGSD-redux/get-shit-done-reduxnpm (main) get-shit-done-ccget-shit-done-reduxnpm (sdk) @gsd-build/sdk@gsd-redux/sdkIssue numbers per source renumbered; original is in body as [from gsd-build/get-shit-done#N]If you can reach the original maintainer, please open an issue here and CC them. If you have technical evidence that materially changes the picture above, please share it in an issue.
— trek-e, fork maintainer
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-redux@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-redux@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-redux@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-redux --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.