`init phase-op` only checked disk for phase directories, failing on
phases with Plans: TBD since no directory exists yet. Now falls back
to parsing ROADMAP.md when findPhaseInternal returns null.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Hooks had hardcoded `.claude` paths that broke OpenCode users. The
installer now templates `.js` hooks with runtime-specific config dirs,
same as it already does for `.md` files. Also added `./.claude/`
replacement for local install paths in workflows.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Parser now accepts both `## Phase X:` and `### Phase X:` headers
- `roadmap get-phase` detects when phases exist in summary list but
missing detail sections, returns `error: 'malformed_roadmap'`
- `roadmap analyze` returns `missing_phase_details` array
- Updated gsd-roadmapper instructions with explicit format requirements
- Added 2 tests for new functionality (77 total, all passing)
Closes#598, closes#599
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The verifier agent interpreted {phase} as the full directory slug
(e.g., 01-foundation-target-system) instead of just the padded phase
number (01), producing wrong filenames like
01-foundation-target-system-VERIFICATION.md.
Changed all {phase}-*.md references to {phase_num}-*.md to match the
convention used in gsd-tools.js (${padded}-VERIFICATION.md).
Files: VERIFICATION.md, RESEARCH.md, CONTEXT.md, UAT.md patterns.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Projects with "type": "module" in package.json cause GSD scripts to fail
with "require is not defined" because Node.js walks up the directory tree
and inherits the module type.
Fix: Write {"type":"commonjs"} package.json to the install target (.claude/)
during installation. This stops Node from inheriting the project's ESM config.
- Install: writes package.json after VERSION file
- Uninstall: removes package.json only if it matches our marker
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add X (Twitter) badge linking to @gsd_foundation
- Add $GSD token badge linking to Dexscreener
- Fix Discord badge to show live member count (server ID 1463221958777901349)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add `websearch` command to gsd-tools.js for Brave API
- Detect BRAVE_API_KEY env var or ~/.gsd/brave_api_key file
- Persist brave_search setting to config.json on project init
- Update researcher agents to check config before calling
Graceful degradation: if brave_search is false, agents use
built-in WebSearch without wasted Bash calls.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Runs research → requirements → roadmap automatically after config
questions. Requires idea document via @ reference. Auto-includes all
table stakes features plus features mentioned in provided document.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
On Windows, child.unref() alone is insufficient for proper process
detachment. The child process remains in the parent's process group,
causing Claude Code to wait for the hook process tree to exit before
accepting input.
Adding detached: true allows the child process to fully detach on
Windows while maintaining existing behavior on Unix.
Closes#466
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- git tag command in complete-milestone.md used HEREDOC syntax
- HEREDOC fails silently on Windows Git Bash
- Literal newlines in quoted strings work cross-platform
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When user selects "Skip research" during /gsd:new-milestone, the choice
was not saved to .planning/config.json. Later, /gsd:plan-phase would
read the default (research: true) and spawn researchers anyway.
- Add `config-set` command to gsd-tools.js for setting nested config values
- Update new-milestone workflow to persist research choice after user decides
Closes#484
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat(gsd-tools): add frontmatter CRUD, verification suite, template fill, and state progression
Four new command groups that delegate deterministic operations from AI agents to code:
- frontmatter get/set/merge/validate: Safe YAML frontmatter manipulation with schema validation
- verify plan-structure/phase-completeness/references/commits/artifacts/key-links: Structural checks agents previously burned context on
- template fill summary/plan/verification: Pre-filled document skeletons so agents only fill creative content
- state advance-plan/record-metric/update-progress/add-decision/add-blocker/resolve-blocker/record-session: Automate arithmetic and formatting in STATE.md
Adds reconstructFrontmatter() + spliceFrontmatter() helpers for safe frontmatter roundtripping,
and parseMustHavesBlock() for 3-level YAML parsing of must_haves structures.
20 new functions, ~1037 new lines.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: wire gsd-tools commands into agents and workflows
- gsd-verifier: use `verify artifacts` and `verify key-links` instead of
manual grep patterns for stub detection and wiring verification
- gsd-executor: use `state advance-plan`, `state update-progress`,
`state record-metric`, `state add-decision`, `state record-session`
instead of manual STATE.md manipulation
- gsd-plan-checker: use `verify plan-structure` and `frontmatter get`
for structural validation and must_haves extraction
- gsd-planner: add validation step using `frontmatter validate` and
`verify plan-structure` after writing PLAN.md
- execute-plan.md: use gsd-tools state commands for position/progress updates
- verify-phase.md: use gsd-tools for must_haves extraction and artifact/link verification
This makes the gsd-tools commands from PR #485 actually used by the system.
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Claude Code v2.1.27+ has a bug where all Task tool agents report
"failed" due to `classifyHandoffIfNeeded is not defined` — a function
called but never defined in the cli.js bundle. The error fires AFTER
all agent work completes, so actual work is always done.
This adds spot-check fallback logic to execute-phase, execute-plan,
and quick workflows: when an agent reports this specific failure,
verify artifacts on disk (SUMMARY.md exists, git commits present).
If spot-checks pass, treat as successful.
Tracked upstream: anthropics/claude-code#24181
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
When users modify GSD workflow files (e.g., adding bug workarounds),
those changes get wiped on every /gsd:update. This adds automatic
backup and guided restore:
**install.js changes:**
- Writes `gsd-file-manifest.json` after install with SHA256 hashes
of every installed GSD file
- Before wiping on update, compares current files against manifest
to detect user modifications
- Backs up modified files to `gsd-local-patches/` directory
- Reports backed-up patches after install completes
**New command: /gsd:reapply-patches**
- LLM-guided merge of backed-up modifications into new version
- Handles cases where upstream also changed the same file
- Reports merge status per file (merged/skipped/conflict)
**update.md changes:**
- Warning text now mentions automatic backup instead of manual
- New step after install to check for and report backed-up patches
Flow: modify GSD file → /gsd:update → modifications auto-backed up →
new version installed → /gsd:reapply-patches → modifications merged back
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The workflow showed the prompt content but didn't wrap it in Task()
with the required subagent_type parameter. This caused the orchestrator
to spawn generic task agents instead of the specialized gsd-executor.
Now shows the full Task() call with subagent_type and model parameters.
Fixes#455
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(execute-phase): pass file paths to subagents instead of content
The --include flag added in fa81821 caused orchestrator context bloat
by reading STATE, config, and plan files into the orchestrator's context,
then embedding all content in Task() prompts.
With multiple plans, this consumed 50-60%+ of context before execution.
Fix: Pass file paths only. Subagents read files themselves in their
fresh 200k context. Orchestrator stays lean (~10-15% as intended).
Fixes#479
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: respect commit_docs=false in execute-plan and debugger workflows
Two code paths bypassed the commit_docs configuration check, causing
.planning files to be intermittently committed when commit_docs=false:
1. execute-plan.md: update_codebase_map step ran `git add .planning/codebase/*.md`
unconditionally — now gated behind commit_docs check
2. gsd-debugger.md: used `git add -A` which stages .planning/ files — replaced
with explicit individual file staging and proper commit_docs conditional
Fixes#478https://claude.ai/code/session_013yS1F2VR3Jn2pdwqr5NuDo
* fix: route all .planning commits through gsd-tools.js CLI
Instead of wrapping direct git commands in markdown conditionals,
both bypass paths now use gsd-tools.js commit which has the
commit_docs check built in:
1. execute-plan.md: uses `gsd-tools.js commit --amend` for codebase
map updates (new --amend flag added to CLI)
2. gsd-debugger.md: code commit uses direct git (no .planning files),
planning docs commit uses gsd-tools.js commit
Also added --amend support to gsd-tools.js commit command so the
execute-plan codebase map step can amend the previous metadata commit.
Fixes#478https://claude.ai/code/session_013yS1F2VR3Jn2pdwqr5NuDo
* docs: update reference docs to use gsd-tools.js CLI for all .planning commits
Reference documentation showed direct git add/commit patterns for
.planning files, which agents copy-paste and bypass the commit_docs
check. Updated all three reference files to show gsd-tools.js commit
as the canonical pattern:
- git-planning-commit.md: replaced manual bash conditionals with CLI
- git-integration.md: replaced direct git add/commit in initialization,
plan-completion, and handoff examples
- planning-config.md: replaced conditional git example with CLI call
https://claude.ai/code/session_013yS1F2VR3Jn2pdwqr5NuDo
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
On Windows, path.join(os.homedir(), '.cursor') produces backslash paths (e.g. C:\Users\user\.cursor). When appended with forward slashes to build pathPrefix, this creates mixed-separator paths that break gsd-tools invocations:
Bash(node C:\Users\user\.claude/get-shit-done/bin/gsd-tools.js init map-codebase)
Normalize targetDir and opencodeConfigDir to forward slashes before concatenation so Node.js receives consistent paths on all platforms.
Co-authored-by: Cursor <cursoragent@cursor.com>
Workflows were calling init commands to get parsed JSON metadata, then
immediately reading the same files again with cat to pass raw content
to agents. This wastes context tokens.
Changes:
- Add --include flag to init execute-phase, plan-phase, and progress
- Support includes: state, config, roadmap, requirements, context,
research, verification, uat, project
- Update plan-phase.md to use --include (removes 6 cat calls)
- Update execute-phase.md to use --include (removes 2 cat calls)
- Update execute-plan.md to use --include (removes 2 cat calls)
- Update progress.md to use --include (removes 4 cat calls)
- Add 7 tests for --include functionality
Token savings: ~5,000-10,000 tokens per plan-phase execution,
~1,500-3,000 per other workflow executions.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
