Claude Code subagents sometimes rewrite ~/. paths to relative paths,
causing MODULE_NOT_FOUND when CWD is the project directory. $HOME is a
shell variable resolved at runtime, immune to model path rewriting.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- gsd-executor: Add <analysis_paralysis_guard> block after deviation_rules.
If executor makes 5+ consecutive Read/Grep/Glob calls without any
Edit/Write/Bash action, it must stop and either write or report blocked.
Prevents infinite analysis loops that stall execution.
- gsd-plan-checker: Add exhaustive cross-check in Step 4 requirement coverage.
Checker now also reads PROJECT.md requirements (not just phase goal) to
verify no relevant requirement is silently dropped. Unmapped requirements
become automatic blockers listed explicitly in issues.
- gsd-planner: Add task-level TDD guidance alongside existing TDD Detection.
For code-producing tasks in standard plans, tdd="true" + <behavior> block
makes test expectations explicit before implementation. Complements the
existing dedicated TDD plan approach — both can coexist.
Co-authored-by: CyPack <GITHUB_EMAIL_ADRESIN>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: use `.claude/skills/` instead of `.agents/skills/` in agent and workflow skill references
Claude Code resolves project skills from `.claude/skills/` (project-level)
and `~/.claude/skills/` (user-level). The `.agents/skills/` path is the
universal/IDE-agnostic convention that Claude Code does not resolve, causing
project skills to be silently ignored by all affected agents and workflows.
Fixes#758
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: support both `.claude/skills/` and `.agents/skills/` for cross-IDE compatibility
Instead of replacing `.agents/skills/` with `.claude/skills/`, reference both
paths so GSD works with Claude Code (`.claude/skills/`) and other IDE agents
like OpenCode (`.agents/skills/`).
Addresses review feedback from begna112 on #758.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Stephen Miller <Stephen@betterbox.pw>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The verifier was the only agent missing the <project_context> section
that executor, planner, researcher, and plan-checker all have. This
aligns it with the existing pattern so project skills and CLAUDE.md
instructions are applied during verification and anti-pattern scanning.
Closes discussion from PR #723.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reduces token overhead of Dimension 8 and related agent additions by ~37%
with no behavioral change. Removes theory explanation, dead XML tags
(<manual>, <sampling_rate>), aspirational execution tracking, and
documentation-density prose from runtime agent bodies.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Adds automated feedback architecture research to gsd-phase-researcher,
enforces it as Dimension 8 in gsd-plan-checker, and introduces
{phase}-VALIDATION.md as the per-phase validation contract.
Ensures every phase plan includes automated verify commands before
execution begins. Opt-out via workflow.nyquist_validation: false.
Closes#122 (partial), related #117
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Subagents now read project-level CLAUDE.md if it exists:
- Workflows: execute-phase, plan-phase, quick
- Agents: gsd-executor, gsd-planner, gsd-phase-researcher, gsd-plan-checker
Agents read ./CLAUDE.md in their fresh context, following project-specific
guidelines, security requirements, and coding conventions.
Fixes: #671
Co-Authored-By: Claude <noreply@anthropic.com>
gsd-executor had no instruction to update ROADMAP or REQUIREMENTS after
completing a plan — both stayed unchecked throughout milestone execution.
- Add `roadmap update-plan-progress` call to executor state_updates
- Add `requirements mark-complete` CLI command to gsd-tools
- Wire requirement marking into executor and execute-plan workflows
- Include ROADMAP.md and REQUIREMENTS.md in executor final commit
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Closes five gaps where requirements could slip through unchecked at milestone
level: audit now cross-references VERIFICATION.md + SUMMARY frontmatter +
REQUIREMENTS.md traceability, integration checker receives req IDs, gap objects
carry plan-level detail, plan-milestone-gaps updates traceability, and
complete-milestone gates on requirements status.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Tighten all requirements references to use MUST/REQUIRED/CRITICAL language
instead of passive suggestions. Close the verification loop by extracting
phase requirement IDs from ROADMAP and passing them through the full chain:
researcher receives IDs → planner writes to PLAN frontmatter → executor
copies to SUMMARY → verifier cross-references against REQUIREMENTS.md with
orphan detection.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Write workflow.auto_advance to config.json so auto-mode survives
context compaction (re-read from disk on every workflow init)
- Auto-approve human-verify and auto-select first option for decision
checkpoints in both executor and orchestrator
- Pass --auto flag from plan-phase to execute-phase spawn
- Clear auto_advance on milestone complete (Route B)
- Document auto-mode checkpoint behavior in golden rules
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Only auto-fix issues directly caused by current task's changes
- Log pre-existing/unrelated issues to deferred-items.md instead of fixing
- Cap auto-fix attempts at 3 per task to prevent infinite build/fix loops
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Projects with "type": "module" in package.json cause Node to treat
gsd-tools.js as ESM, crashing on require(). The .cjs extension forces
CommonJS regardless of the host project's module configuration.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Agents (executor, verifier, planner) were writing markdown files via
Bash heredocs. When approved, Claude Code persisted the entire heredoc
as a permission entry, breaking settings.local.json on next launch.
Added explicit "use Write tool" directives to all three agents and
added missing Write tool to gsd-verifier's tool list.
Closes#526Closes#491
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The verifier was deriving verification truths from the vague one-line Goal
field, allowing partial implementations to pass. Now extracts Success Criteria
as a structured array from `roadmap get-phase` and uses them directly as truths,
with Goal derivation as fallback for older ROADMAPs without Success Criteria.
Co-Authored-By: Claude Opus 4.6 <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>
- 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>
* 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>
* 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>
Reverts af7a057 "feat: add GSD Memory cross-project knowledge system"
The memory system needs more work before shipping:
- Workflow integration is incomplete (writes but doesn't query)
- UX requires too much manual intervention
- Setup friction exceeds value for most users
Preserved on branch `memory-wip` for continued development.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements MCP server for semantic search across GSD projects:
MCP Tools:
- gsd_memory_search: Search across all registered projects
- gsd_memory_decisions: Find decisions from SUMMARY/PROJECT.md
- gsd_memory_patterns: Find patterns from SUMMARY.md
- gsd_memory_pitfalls: Find pitfalls from RESEARCH.md
- gsd_memory_stack: Find tech stack entries
- gsd_memory_register: Register project with memory
- gsd_memory_index: Trigger indexing/update
- gsd_memory_status: Show system status
Architecture:
- QMD wrapper with grep fallback when QMD unavailable
- YAML frontmatter extractors for GSD document types
- Project registry at ~/.gsd/projects.json
- Auto-install via bin/install.js for Claude Code
Workflow integrations:
- new-project: Registers project with memory
- plan-phase: Indexes after planning
- execute-phase: Indexes after execution
- complete-milestone: Indexes milestone completion
- Researcher agents query memory before Context7
Tests: 117 passing (66 unit + 51 integration)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Executor self-check after SUMMARY.md creation verifies key-files exist
on disk and commit hashes exist in git log. Orchestrator spot-checks
SUMMARY claims before trusting and proceeding to next wave. Segmented
execution (execute-plan.md) gets the same self-check inline.
Fixes#343
The agent was misinterpreting commit_docs=false as 'skip file write'
when it should only skip git commit operations.
Changes:
- Explicitly state Write tool is mandatory in Step 5
- Clarify commit_docs only affects git operations, not file writes
- Rename Step 6 to indicate it's optional
- Make the file-write-then-commit order explicit
* prompt(001): map dependencies for new-project command
* fix(#326): enforce context fidelity in planning pipeline
Root cause: User decisions from CONTEXT.md were available but not
enforced throughout the RESEARCH → PLAN → VERIFY chain.
Changes:
- gsd-planner: Add <context_fidelity> section requiring agents to
parse and honor user decisions BEFORE creating tasks. Includes
self-check checklist and conflict handling guidance.
- gsd-phase-researcher: Add User Constraints as FIRST section in
downstream consumer table. Require researcher to copy CONTEXT.md
decisions verbatim to RESEARCH.md so planner sees them even if
it only skims.
- research.md template: Add <user_constraints> section that must
be populated first. Locked decisions, Claude's discretion, and
deferred ideas copied verbatim from CONTEXT.md.
The command file (commands/gsd/plan-phase.md) already passes
CONTEXT_CONTENT to all agents. These changes add the enforcement
layer in the agent instructions.
Fixes#326, #216, #206
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
CONTEXT.md from /gsd:discuss-phase now flows through entire pipeline:
- Loaded early in step 4, stored for all agent spawns
- Researcher: constrains research scope (locked decisions vs discretion)
- Planner: explicit guidance to honor locked decisions
- Checker: new Context Compliance dimension to verify plans respect user vision
- Revision: reminder to maintain context compliance during fixes
Adds Dimension 7 (Context Compliance) to gsd-plan-checker:
- Verifies locked decisions have implementing tasks
- Flags if tasks contradict locked decisions
- Flags if deferred ideas included in plans
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* docs: enforce automation-first checkpoint verification
Checkpoints should never ask users to run CLI commands that Claude Code
can execute. This update reinforces the automation-first principle:
Key changes:
- Add golden rules: Claude runs CLI, users only visit URLs
- Add dev server automation patterns (start before checkpoint)
- Add environment variable CLI patterns (Convex, Vercel, etc.)
- Add anti-patterns: asking user to run npm, add dashboard env vars
- Update all examples to show Claude starting servers
- Add comprehensive "Never Ask Users To" and "Users Only Do" lists
- Update gsd-executor with pre-checkpoint automation requirements
The core principle: if Claude CAN automate it, Claude MUST automate it.
Users only do what requires human judgment (visual verification, UX).
* refactor: DRY checkpoint automation with server lifecycle and error handling
Changes:
- checkpoints.md is now single source of truth for automation-first patterns
- Added server lifecycle protocol (start, port conflicts, cleanup)
- Added CLI installation handling (auto-install matrix)
- Added pre-checkpoint failure handling (fix before checkpoint)
- Removed ~93 lines of duplication from verification-patterns.md
- Replaced inline examples in phase-prompt.md with references
- Slimmed gsd-executor.md checkpoint section to reference checkpoints.md
Net effect: -23 lines while adding 3 new capabilities (server lifecycle,
CLI install, error handling). Single place to update automation patterns.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Rolled back the intel system due to overengineering concerns:
- 1200+ line hook with SQLite graph database
- 21MB sql.js dependency
- Entity generation spawning additional Claude calls
- Complex system with unclear value
Removed:
- /gsd:analyze-codebase command
- /gsd:query-intel command
- gsd-intel-index.js, gsd-intel-session.js, gsd-intel-prune.js hooks
- gsd-entity-generator, gsd-indexer agents
- entity.md template
- sql.js dependency
Preserved:
- Model profiles feature
- Statusline hook
- All other v1.9.x improvements
-3,065 lines removed
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create indexer agent for Steps 2-3 file indexing
- Uses exact regex patterns from analyze-codebase Step 3
- Writes index.json directly to disk (context preservation)
- Returns statistics only to orchestrator
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add agent for semantic entity generation from source files
- Include entity template with frontmatter, purpose, exports, deps
- Define type heuristics table for module classification
- Specify wiki-link rules for internal vs external dependencies
- Agent writes directly to .planning/intel/entities/
- Returns statistics only (not entity contents)
- Add load_codebase_intelligence step to gsd-planner.md
- Add load_codebase_intelligence step to gsd-executor.md
- Include .planning/intel/summary.md in plan context template
- Subagents now use detected conventions during planning/execution
* feat: add uncommitted planning mode
Add config option to keep planning docs local-only (not committed to git).
Useful for OSS contributions, client projects, or keeping planning private.
Config options in .planning/config.json:
- planning.commit_docs: true/false (default: true)
- planning.search_gitignored: true/false (default: false)
When commit_docs=false:
- All git operations for .planning/ files are skipped
- User should add .planning/ to .gitignore
- Planning system works normally, just not tracked
Updated files:
- config.json template: added planning section
- execute-plan.md: conditional git commits
- execute-phase.md: conditional git commits
- create-roadmap.md: conditional git commits
- help.md: documented new config options
- planning-config.md: reference doc for config behavior
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: extend commit_docs check to all agents/commands/workflows
Add COMMIT_PLANNING_DOCS config check to all files that commit
.planning/ artifacts, ensuring consistent behavior when
commit_docs=false is set in config.json.
Updated:
- 5 agents (planner, executor, debugger, phase-researcher, synthesizer)
- 8 commands (add-todo, check-todos, execute-phase, new-milestone,
pause-work, plan-milestone-gaps, remove-phase, research-project)
- 7 workflows (complete-milestone, create-milestone, define-requirements,
diagnose-issues, discuss-phase, map-codebase, verify-work)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(progress): use Bash instead of Glob for .planning/ check
Glob respects .gitignore, so projects with gitignored .planning/
directories would fail with "No planning structure found."
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(new-milestone): integrate full research/requirements/roadmap flow
Previously routed to non-existent /gsd:research-project and
/gsd:define-requirements commands. Now handles the full flow inline
like new-project does:
- Phase 7: Research Decision (spawns 4 milestone-aware researchers)
- Phase 8: Define Requirements (scopes features, creates REQUIREMENTS.md)
- Phase 9: Create Roadmap (continues phase numbering from previous milestone)
- Phase 10: Done
Key adaptations for milestones:
- Research focuses on NEW features only
- Requirements add to existing, don't start fresh
- Phase numbering continues from previous milestone
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Researcher agents were using literal "2025" in query template examples,
causing Claude to copy them verbatim instead of using the actual current
year. Changed to [current year] placeholder with explicit instruction to
check today's date.
Fixes#164
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
After verify-work diagnoses issues and creates fix plans, the next
command now explicitly signals intent with --gaps-only. This eliminates
redundant state discovery where execute-phase had to figure out why it
was being asked to run on an already-complete phase.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
