e437ded6fc
* docs(3524): propose CJS↔SDK hard-seam ADR + phased PRD Adds docs/adr/3524-cjs-sdk-hard-seam.md (Proposed) and docs/prd/3524-cjs-sdk-hard-seam.md (Reference) tracking #3524. Updates the ADR and PRD index READMEs. The ADR defines one canonical owner per responsibility across the CJS (bin/lib/*.cjs) and SDK (sdk/src/**/*.ts) sides, eliminating the recurring drift bug class (#1535, #1542, #2047, #2638, #2653, #2687, #2798, #3055, #3523). Three layers: shared data (sdk/shared/*.json), shared core logic (sdk/src/core/ → dual CJS+ESM build), thin adapters. Enforcement is layered: build-time grep, type-level contract test, mutation parity test, CODEOWNERS gate, in-file banner. The PRD phases the migration in five independently shippable steps — shared data first (closes constant drift), then config consolidation (closes #3523 class), then project-root + path projection, then state and verify handlers, then enforcement hardening + retrospective. * docs(3524): revise seam ADR + PRD after architecture review Architecture-review pass (via /improve-codebase-architecture) found seven deepening opportunities; this commit applies all of them. 1. Re-anchor on the existing generator precedent. The repo already has sdk/scripts/gen-command-aliases.ts emitting both .generated.ts and .generated.cjs from one TS source, with sdk/scripts/check-command-aliases-fresh.mjs as the CI freshness gate. The ADR's invented dual CJS+ESM bundler pipeline is dropped. Each Shared Module gets one generator script and one freshness check, modeled on that precedent. 2. Drop the generic sdk/src/core/ container. The canonical-owner table is now indexed by Module, using the CONTEXT.md domain vocabulary (STATE.md Document Module, Configuration Module, etc.) rather than file-path-based pseudo-modules. 3. Split the coarse "State management" row into three: the pure STATE.md Document Module (already a character-identical hand-synced pair — perfect Phase 1 target), the Planning Workspace Module (defer to ADR-0004), and per-side state I/O Adapters (legitimately differ sync vs async). 4. Defer to existing ADRs. Planning Path Projection (ADR-0006), Model Catalog (ADR-0003), Planning Workspace (ADR-0004), Dispatch Policy (ADR-0001), Shell Command Projection (ADR-0009 post-Phase 3-4 expansion which absorbed superseded ADR-0010). The stale ADR-0010 reference is fixed. 5. Define a Configuration Module entry in CONTEXT.md as a Phase 2 deliverable, with explicit Interface contract for loadConfig, normalizeLegacyKeys, mergeDefaults, migrateOnDisk. 6. Split the Workstream Inventory Module into a pure Builder (generated, shared) and per-side Reader Adapters (hand-authored, sync vs async). Same pattern generalizes to other paired Modules. 7. Match enforcement to existing scripts. Per-Module freshness checks (precedent: check-command-aliases-fresh.mjs), per-Module drift lints (precedent: lint-shell-command-projection-drift.cjs), and one hand-sync pair lint that blocks the #3523 anti-pattern at PR time. PRD phases reordered: STATE.md Document Module ships first as a proof of pattern (two identical files become one source plus one generated artifact). Configuration Module ships second, closing the #3523 class. Workstream Inventory Builder split third. Project-Root Resolution fourth. Enforcement and retrospective fifth. * docs(3524): expand scope — CJS router delegates to SDK runtime bridge User flagged that the original "Out of scope" list was my unilateral scoping call, not theirs. After review, the CJS router consolidation (formerly out-of-scope item #1) is brought into scope. ADR additions: - CJS Command Router Adapter Module row added to canonical-owner table. Existing Module (per CONTEXT.md) is amended so the per-family `handlers` map delegates to `QueryRuntimeBridge.execute()` in-process. Per-side CJS handler files for canonical families (state.cjs, verify.cjs, init.cjs, phase.cjs, etc.) shrink to delegates or are deleted. - Per-side I/O Adapter consequence updated to clarify the bridge preserves the in-process model. No subprocess hop is added. - "Out of scope" stripped of router item; CJS-only seam migration and verify-Module-first work remain out of scope. PRD additions: - New Phase 5: CJS Command Router Adapter delegates to SDK runtime bridge, family-by-family, with golden parity matrix per family gating each PR. - Old Phase 5 (enforcement) renumbered to Phase 6, expanded to cover Phase 5's parity matrix and runtime-bridge CODEOWNERS. - Open question #4 added for the synchronous-bridging mechanism (`deasync` vs `Atomics.wait` vs sync-handler refactor) — resolved in the Phase 5 spike before any family migration begins. - Open question #5 added for family migration order (recommended: smallest read-only family first). - Risks table expanded with three Phase 5 rows: bridging-mechanism uncertainty, observable-output regression, startup-time impact. - Done-when updated for six phases and five enforcement layers. Non-goals updated: CJS-only Module migration and verify-Module deepening remain out of scope. CJS CLI removal explicitly stays off the table — the external `gsd-tools` contract is preserved. * docs(3524): address CodeRabbit review * docs(3524): fix PRD issue reference markdown
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.
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.