b533f71857
* feat(routing): add CommandRoutingHub with behavioral test suite (#3788) Introduces createHub({ mode, sdkLoader, cjsRegistry, manifest }) and hub.dispatch({ family, subcommand, args, cwd, raw }) -> Result with a closed 6-value ERROR_KINDS frozen enum. Hub never throws, never prints, and enforces no transparent fallback between sdk/cjs modes. 34 behavioral tests cover all errorKind values, mode fixation, and the no-throw contract. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * refactor(routing): migrate phase-command-router to CommandRoutingHub (#3788) Rewrites phase-command-router.cjs to dispatch through CommandRoutingHub. Public entry point routePhaseCommand({ phase, args, cwd, raw, error }) is unchanged. The adapter determines mode (sdk/cjs) from env + tryLoadSdk(), constructs a hub, dispatches, and translates the pure Result back to output()/error() calls. New behavioral test suite (23 tests) replaces the old mock-heavy approach and includes two integration tests through the real hub. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs(routing): ADR + glossary + changeset for CommandRoutingHub (#3788) Adds ADR-3788 documenting the hub's design contract (pure result, fixed mode, closed 6-value errorKind enum, no transparent fallback). Adds Command Routing Hub glossary entry to CONTEXT.md and a one-paragraph reference to ARCHITECTURE.md. Changeset fragment records the Changed entry. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(docs): rename ADR to sequential convention 0012 (#3788) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs(inventory): register CommandRoutingHub in INVENTORY (#3788) Add command-routing-hub.cjs row to docs/INVENTORY.md CLI Modules table, bump headline count from 72 to 73, and regenerate INVENTORY-MANIFEST.json via scripts/gen-inventory-manifest.cjs --write. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs(adr): add 0012 to ADR index (#3788) Add entry for 0012-command-routing-hub.md to the index table in docs/adr/README.md so the enh-3271-sdk-adr-structure lint passes. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * chore(lint): bump phase test-file ceiling to accommodate command-router suite (#3788) phase-command-router.test.cjs added by the CommandRoutingHub migration pushes the phase prefix cluster from 4 to 5 test files. Bump the allowlist ceiling from 4 to 5 (issue 3788) so lint-test-file-count passes. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(routing): preserve phase.mvp-mode JSON error and ROADMAP scan through hub (#3788) mvp-mode was never registered in the SDK; the pre-#3788 CJS router always dispatched it via the CJS handler even when sdkAvailable was true. After the hub migration, SDK-mode hubs (Docker, where the SDK build exists) sent mvp-mode to the SDK bridge, which returned SdkDispatchFailed with reason 'unknown' instead of the expected 'usage' code, and failed ROADMAP lookups. Fix by short-circuiting mvp-mode to the CJS handler before hub construction, matching the pre-migration observable behaviour. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs(adr): note SDK-incomplete subcommand limitation in ADR-0012 (#3788) * fix(inventory): bump CLI Modules headline to 74 after rebase onto main (#3788) Upstream added code-review-flags.cjs (72→73) at the same time our branch added command-routing-hub.cjs. After rebase both modules exist (74 total) but the headline stayed at 73; bump to 74. * fix(routing): remove dead mvp-mode handler from cjsRegistry (#3788) The cjsRegistry['phase']['mvp-mode'] handler (previously lines 65–68) was unreachable: the early-return bypass at line 56 intercepts mvp-mode before hub construction in CJS mode, and in SDK mode cjsRegistry is passed as undefined. Remove the dead handler; all 57 tests still pass. * docs(adr): correct router count in ADR-0012 (#3788) The context section cited "eight" routers including "frontmatter" but there is no frontmatter-command-router.cjs. The actual count is seven: phase, phases, roadmap, state, verify, validate, init. * fix(routing): guard missing subcommand + use ERROR_KINDS constant (#3788) Two fixes in phase-command-router.cjs: 1. Add early-return for missing subcommand before hub construction. Pre-#3788 the routeCjsCommandFamily fell through to error() for undefined args[1]; post-#3788 the hub's manifest check skips falsy subcommands, which would have sent bare 'phase' into SDK dispatch in SDK mode instead of the expected "Available: ..." error message. 2. Switch on ERROR_KINDS.UnknownCommand instead of bare 'UnknownCommand' string, per ADR-0012's closed-enum contract ("callers switch on ERROR_KINDS values, not bare string literals"). * docs(routing): fix factual errors in ARCHITECTURE, ADR-0012, changeset (#3788) Three corrections: 1. ARCHITECTURE.md: softened "All CJS command family routers dispatch through CommandRoutingHub" — only phase-command-router.cjs is migrated in this PR; remaining routers still use routeCjsCommandFamily and migrate in follow-up issues. 2. ADR-0012: corrected the SDK mvp-mode claim. The ADR said "the SDK has no equivalent entry" but sdk/src/query/command-static-catalog- domain.ts:104-105 registers phase.mvp-mode. The actual reason for the early-return bypass is divergent ROADMAP scan behaviour and error reason codes, not SDK absence. 3. .changeset/mellow-tigers-gather.md: corrected pr: 1 → pr: 3828. --------- 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.