Integrate Exa (semantic search) and Firecrawl (deep web scraping) as
MCP-based research tools, following the existing Brave Search pattern.
- Add tool declarations to all 3 researcher agents
- Add tool strategy sections with usage guidance and priority
- Add config detection for FIRECRAWL_API_KEY and EXA_API_KEY env vars
- Add firecrawl/exa_search config keys to core defaults and init output
- Update source priority hierarchy across all researchers
Adds an optional advisor mode to discuss-phase that provides research-backed
comparison tables before asking users to make decisions. Activates when
USER-PROFILE.md exists, degrades gracefully otherwise.
New agent: gsd-advisor-researcher -- spawned in parallel per gray area,
returns structured 5-column comparison tables calibrated to the user vendor
philosophy preference (full_maturity/standard/minimal_decisive).
Workflow changes (discuss-phase.md):
- Advisor mode detection in analyze_phase step
- New advisor_research step spawns parallel research agents
- Table-first discussion flow in discuss_areas when advisor mode active
- Standard conversational flow unchanged when advisor mode inactive
The hash recording step used `git rev-parse --short HEAD` which fails
when the project root is not a git repo (multi-repo workspaces). Update
the protocol to extract hashes from commit-to-subrepo JSON output and
record all sub-repo hashes in the SUMMARY.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add support for workspaces with multiple independent git repositories.
When configured, GSD routes commits to the correct sub-repo and ensures
.planning/ stays at the project root.
Core features:
- detectSubRepos(): scans child directories for .git to discover repos
- findProjectRoot(): walks up from CWD to find the project root that
owns .planning/, preventing orphaned .planning/ in sub-repos
- loadConfig auto-syncs sub_repos when repos are added or removed
- Migrates legacy "multiRepo: true" to sub_repos array automatically
- All init commands include project_root in output
- cmdCommitToSubrepo: groups files by sub-repo prefix, commits independently
Zero impact on single-repo workflows — sub_repos defaults to empty array.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds a Runtime State Inventory step that fires when a phase involves
renaming, rebranding, refactoring, or migrating strings across a codebase.
The core problem: grep audits find files. They do NOT find runtime state —
ChromaDB collection names, Mem0 user_ids, n8n workflows in SQLite, Windows
Task Scheduler descriptions, pm2 process names, SOPS key names, pip
egg-info directories, etc. These survive a complete file-level rename and
will break the system silently after the code is "done".
Three additions:
1. Pre-Submission Checklist — adds a reminder item so the checklist gate
catches skipped inventories before RESEARCH.md is committed
2. output_format — adds Runtime State Inventory table to the RESEARCH.md
template so the section appears in every rename/refactor phase's output
3. execution_flow Step 2.5 — structured investigation protocol with the
five categories (stored data, live service config, OS-registered state,
secrets/env vars, build artifacts), explicit examples for each, and the
canonical question that frames the whole exercise
Three additive quality improvements to the execution pipeline:
1. Pre-wave dependency check (execute-phase): Before spawning wave N+1,
verify key-links from prior wave artifacts. Catches cross-plan wiring
gaps before they cascade into downstream failures.
2. Cross-Plan Data Contracts dimension (plan-checker): New Dimension 9
checks that plans sharing data pipelines have compatible transformations.
Flags when one plan strips data another plan needs in original form.
3. Export-level spot check (verify-phase): After Level 3 wiring passes,
spot-check individual exports for actual usage. Catches dead stores
that exist in wired files but are never called.
The researcher agent now verifies each recommended package version
using 'npm view [package] version' before writing the Standard Stack
section. This prevents recommending stale versions from training data.
Addresses patch 5 from #899
After committing task changes, the executor now checks for untracked
files (git status --short | grep '^??') and handles them: commit if
intentional, add to .gitignore if generated/runtime output.
This prevents generated artifacts (build outputs, .env files, cache
files) from being silently left untracked in the working tree.
Changes:
- execute-plan.md: Add step 6 to task commit protocol
- gsd-executor.md: Add step 6 to task commit protocol
Fixes#957
Strip unsupported `skills:` key from gsd-ui-auditor, gsd-ui-checker, and
gsd-ui-researcher agent frontmatter. Update Copilot install test expectations
to 36 skills / 15 agents.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When a debug session resolves, append a structured entry to
.planning/debug/knowledge-base.md capturing error patterns,
root cause, and fix approach.
At the start of each new investigation (Phase 0), the debugger
loads the knowledge base and checks for keyword overlap with
current symptoms. Matches surface as hypothesis candidates to
test first — reducing repeat investigation time for known patterns.
The knowledge base is append-only and project-scoped, so it
builds value over the lifetime of a codebase rather than
resetting each session.
Add pre-planning design contract generation and post-execution visual audit
for frontend phases. Closes the gap where execute-phase runs without a visual
contract, producing inconsistent spacing, color, and typography across components.
New agents: gsd-ui-researcher (UI-SPEC.md), gsd-ui-checker (6-dimension
validation), gsd-ui-auditor (6-pillar scored audit + registry re-vetting).
Third-party shadcn registry blocks are machine-vetted at contract time,
verification time, and audit time — three enforcement points, not a checkbox.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove dangling skills: from agent frontmatter and strip in Gemini converter (closes#1023, closes#953, closes#930)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: invert skills frontmatter test to assert absence (fixes CI)
The PR deliberately removed skills: from agent frontmatter (breaks
Gemini CLI), but the test still asserted its presence. Inverted the
assertion to ensure skills: stays removed.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When gsd-tools init output exceeds 50KB, core.cjs writes to a temp file
and outputs @file:<path>. No workflow handled this prefix, causing agents
to hallucinate /tmp paths that fail on Windows (C:\tmp doesn't exist).
Add @file: resolution line after every INIT=$(node ...) call across all
32 workflow, agent, and reference files.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: change nyquist_validation default to true and harden absent-key skip conditions
new-project.md never wrote the key, so agents reading config directly
treated absent as falsy. Changed all agent skip conditions from "is false"
to "explicitly set to false; absent = enabled". Default changed from false
to true in core.cjs, config.cjs, and templates/config.json.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: enforce VALIDATION.md creation with verification gate and Check 8e
Step 5.5 was narrative markdown that Claude skipped under context pressure.
Now MANDATORY with Write tool requirement and file-existence verification.
Step 7.5 gates planner spawn on VALIDATION.md presence. Check 8e blocks
Dimension 8 if file missing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add W008/W009 health checks and addNyquistKey repair for Nyquist drift detection
W008 warns when workflow.nyquist_validation key is absent from config.json
(agents may skip validation). W009 warns when RESEARCH.md has Validation
Architecture section but no VALIDATION.md file exists. addNyquistKey repair
adds the missing key with default true value.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add /gsd:validate-phase command and gsd-nyquist-auditor agent
Retroactively applies Nyquist validation to already-executed phases.
Works mid-milestone and post-milestone. Detects existing test coverage,
maps gaps to phase requirements, writes missing tests, debugs failing
ones, and produces {phase}-VALIDATION.md from existing artifacts.
Handles three states: VALIDATION.md exists (audit + update), no
VALIDATION.md (reconstruct from PLAN.md + SUMMARY.md), phase not yet
executed (exit cleanly with guidance).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: audit-milestone reports Nyquist compliance gaps across phases
Adds Nyquist coverage table to audit-milestone output when
workflow.nyquist_validation is true. Identifies phases missing
VALIDATION.md or with nyquist_compliant: false/partial.
Routes to /gsd:validate-phase for resolution. Updates USER-GUIDE
with retroactive validation documentation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: compress Nyquist prompts to match GSD meta-prompt density conventions
Auditor agent: deleted philosophy section (35 lines), compressed execution
flow 60%, removed redundant constraints. Workflow: cut purpose bloat,
collapsed state narrative, compressed auditor spawn template. Command:
removed redundant process section. Plan-phase Steps 5.5/7.5: replaced
hedging language with directives. Audit-milestone Step 5.5: collapsed
sub-steps into inline instructions. Net: -376 lines.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The "depth" setting with values quick/standard/comprehensive implied
investigation thoroughness, but it only controls phase count. Renamed to
"granularity" with values coarse/standard/fine to accurately reflect what
it controls: how finely scope is sliced into phases.
Includes backward-compatible migration in loadConfig and config-ensure
that auto-renames depth→granularity with value mapping in both
.planning/config.json and ~/.gsd/defaults.json.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduce ephemeral `workflow._auto_chain_active` flag to separate chain
propagation from the user's persistent `workflow.auto_advance` preference.
Previously, `workflow.auto_advance` was set to true by --auto chains and
only cleared at milestone completion. If a chain was interrupted (context
limit, crash, user abort), the flag persisted in .planning/config.json
and caused all subsequent manual invocations to auto-advance unexpectedly.
The fix adds a "sync chain flag with intent" step to discuss-phase,
plan-phase, and execute-phase workflows: when --auto is NOT in arguments,
the ephemeral _auto_chain_active flag is cleared. The persistent
auto_advance setting (from /gsd:settings) is never touched, preserving
the user's deliberate preference.
Closes#857
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Gap closure plans hardcode wave: 1 and depends_on: [], bypassing the
standard wave assignment logic. When multiple gap closure plans have
dependencies between them, they all land in wave 1 and execute in
parallel — ignoring dependency ordering. Add an explicit wave
computation step using the same assign_waves algorithm as standard
planning.
Closes#856
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Two defensive hardening changes:
1. state.cjs: Replace two identical inline extractField closures
(cmdStateSnapshot and buildStateFrontmatter) with a shared
stateExtractField(content, fieldName) helper at module scope.
The helper uses escapeRegex on fieldName before interpolation
into RegExp constructors, preventing breakage if a field name
ever contains regex metacharacters. Net removal of duplicated
logic.
2. gsd-plan-checker.md: Bound the "relevant" definition in the
exhaustive cross-check instruction. A requirement is "relevant"
only if ROADMAP.md explicitly maps it to this phase or the phase
goal directly implies it — prevents false blocker flags for
requirements belonging to other phases.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add skills: field to all 11 agent frontmatter files with forward-compatible
GSD workflow skill references (silently ignored until skill files are created).
Add commented hooks: examples to 9 file-writing agents showing PostToolUse
hook syntax for project-specific linting/formatting. Read-only agents
(plan-checker, integration-checker) skip hooks as they cannot modify files.
Per Claude Code docs: subagents don't inherit skills or hooks from the
parent conversation — they must be explicitly listed in frontmatter.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add 'never use heredoc' instruction to 6 agents that were missing it:
gsd-codebase-mapper, gsd-debugger, gsd-phase-researcher,
gsd-project-researcher, gsd-research-synthesizer, gsd-roadmapper.
All 9 file-writing agents now consistently prevent settings.local.json
corruption from heredoc permission entries (GSD #526).
Read-only agents (plan-checker, integration-checker) excluded as they
cannot write files.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
