Replace minutes-based task sizing with context-window percentage sizing.
Add planner_authority_limits section prohibiting difficulty-based scope
decisions. Expand decision coverage matrix to multi-source audit covering
GOAL, REQ, RESEARCH, and CONTEXT artifacts. Add Source Audit gap handling
to plan-phase orchestrator (step 9c). Update plan-checker to detect
time/complexity language in scope reduction scans. Add 374 CI regression
tests preventing prohibited language from leaking back into artifacts.
Closes#2091Closes#2092
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
When CONTEXT_WINDOW < 200000, executor and planner agent prompts strip
extended examples and anti-pattern lists into reference files for
on-demand @ loading, reducing static overhead by ~40% while preserving
behavioral correctness for standard (200K-500K) and enriched (500K+) tiers.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Before framework-specific research, phase-researcher now maps each
capability to its architectural tier owner (browser, frontend server,
API, database, CDN). The planner sanity-checks task assignments against
this map, and plan-checker enforces tier compliance as Dimension 7c.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Running git clean inside a worktree treats files committed on the feature
branch as untracked — from the worktree's perspective they were never staged.
The executor deletes them, then commits only its own deliverables; when the
worktree branch merges back the deletions land on the main branch, destroying
prior-wave work (documented across 8 incidents, including commit c6f4753
"Wave 2 executor incorrectly ran git-clean on the worktree").
- Add <destructive_git_prohibition> block to gsd-executor.md explaining
exactly why git clean is unsafe in worktree context and what to use instead
- Add regression tests (bug-2075-worktree-deletion-safeguards.test.cjs)
covering Failure Mode B (git clean prohibition), Failure Mode A
(worktree_branch_check presence audit across all worktree-spawning
workflows), and both defense-in-depth deletion checks from #1977
Failure Mode A and defense-in-depth checks (post-commit --diff-filter=D in
gsd-executor.md, pre-merge --diff-filter=D in execute-phase.md) were already
implemented — tests confirm they remain in place.
Fixes#2075
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Closes#1885
The upstream bug anthropics/claude-code#13898 causes Claude Code to strip all
inherited MCP tools from agents that declare a `tools:` frontmatter restriction,
making `mcp__context7__*` declarations in agent frontmatter completely inert.
Implements Fix 2 from issue #1885 (trek-e's chosen approach): replace the
`<mcp_tool_usage>` block in gsd-executor and gsd-planner with a
`<documentation_lookup>` block that checks for MCP availability first, then
falls back to the Context7 CLI via Bash (`npx --yes ctx7@latest`). Adds the
same `<documentation_lookup>` block to the six researcher agents that declare
MCP tools but lacked any fallback instruction.
Agents fixed (8 total):
- gsd-executor (had <mcp_tool_usage>, now <documentation_lookup> with CLI fallback)
- gsd-planner (had <mcp_tool_usage>, now compact <documentation_lookup>; stays under 45K limit)
- gsd-phase-researcher (new <documentation_lookup> block)
- gsd-project-researcher (new <documentation_lookup> block)
- gsd-ui-researcher (new <documentation_lookup> block)
- gsd-advisor-researcher (new <documentation_lookup> block)
- gsd-ai-researcher (new <documentation_lookup> block)
- gsd-domain-researcher (new <documentation_lookup> block)
When the upstream Claude Code bug is fixed, the MCP path in step 1 of the block
will become active automatically — no agent changes needed.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The deviation rules and task commit protocol were duplicated between
gsd-executor.md (agent definition) and execute-plan.md (workflow).
The copies had diverged: the agent had scope boundary and fix attempt
limits the workflow lacked; the workflow had 3 extra commit types
(perf, docs, style) the agent lacked.
Consolidate gsd-executor.md as the single source of truth:
- Add missing commit types (perf, docs, style) to gsd-executor.md
- Replace execute-plan.md's ~90 lines of duplicated content with
concise references to the agent definition
Saves ~1,600 tokens per workflow spawn and eliminates maintenance
drift between the two copies.
Closes#1968
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Adds ios-scaffold.md reference that explicitly prohibits Package.swift +
.executableTarget for iOS apps (produces macOS CLI, not iOS app bundle),
requires project.yml + xcodegen generate to create a proper .xcodeproj,
and documents SwiftUI API availability tiers (iOS 16 vs 17). Adds iOS
anti-patterns 28-29 to universal-anti-patterns.md and wires the reference
into gsd-executor.md so executors see the guidance during iOS plan execution.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(worktree): use reset --hard in worktree_branch_check to correctly set base (#2015)
The worktree_branch_check in execute-phase.md and quick.md used
git reset --soft as the fallback when EnterWorktree created a branch
from main/master instead of the current feature branch HEAD. --soft
moves the HEAD pointer but leaves working tree files from main unchanged,
so the executor worked against stale code and produced commits containing
the entire feature branch diff as deletions.
Fix: replace git reset --soft with git reset --hard in both workflow files.
--hard resets both the HEAD pointer and the working tree to the expected
base commit. It is safe in a fresh worktree that has no user changes.
Adds 4 regression tests (2 per workflow) verifying that the check uses
--hard and does not contain --soft.
* fix(worktree): executor deletion verification and pre-merge deletion block (#1977)
- Remove Windows-only qualifier from worktree_branch_check in execute-plan.md
(the EnterWorktree base-branch bug affects all platforms, not just Windows)
- Add post-commit --diff-filter=D deletion check to gsd-executor.md task_commit_protocol
so unexpected file deletions are flagged immediately after each task commit
- Add pre-merge --diff-filter=D deletion guard to execute-phase.md worktree cleanup
so worktree branches containing file deletions are blocked before fast-forward merge
- Add regression test tests/worktree-safety.test.cjs covering all three behaviors
Fixes#1977
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(references): add common bug patterns checklist for debugger
Create a technology-agnostic reference of ~80%-coverage bug patterns
ordered by frequency — off-by-one, null access, async timing, state
management, imports, environment, data shape, strings, filesystem,
and error handling. The debugger agent now reads this checklist before
forming hypotheses, reducing the chance of overlooking common causes.
Closes#1746
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(references): use bold bullet format in bug patterns per GSD convention (#1746)
- Convert checklist items from '- [ ]' checkbox format to '- **label** —'
bold bullet format matching other GSD reference files
- Scope test to <patterns> block only so <usage> section doesn't fail
the bold-bullet assertion
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(references): add gates taxonomy with 4 canonical gate types
Define pre-flight, revision, escalation, and abort gates as the
canonical validation checkpoint types used across GSD workflows.
Includes a gate matrix mapping each workflow phase to its gate type,
checked artifacts, and failure behavior. Cross-referenced from
plan-phase and execute-phase workflows.
Closes#1715
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(agents): add gates.md reference to plan-checker and verifier per approved scope (#1715)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(agents): move gates.md to required_reading blocks and add stall detection (#1715)
- Move gates.md @-reference from <role> prose into <required_reading> blocks
in gsd-plan-checker.md and gsd-verifier.md so it loads as context
- Add stall-detection to Revision Gate recovery description
- Fix /gsd-next → next for consistent workflow naming in Gate Matrix
- Update tests to verify required_reading placement and stall detection
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(agents): auto-inject relevant global learnings into planner context
* fix(agents): address review feedback for learnings planner injection
- Add features.global_learnings to VALID_CONFIG_KEYS for explicit validation
- Fix error message in cmdConfigSet to mention features.<feature_name> pattern
- Clarify tag syntax in planner injection step (frontmatter tags or objective keywords)
* docs(agents): add few-shot calibration examples for plan-checker and verifier
Closes#1723
* test(agents): add structural tests for few-shot calibration examples
Validates reference file existence, frontmatter metadata, example counts,
WHY annotations on every example, agent @reference lines, and content
structure (input/output pairs, calibration gap patterns table).
Combines implementation by @davesienkowski (inline @-reference wiring at
decision-point steps, named reasoning models with anti-patterns, sequencing
rules, Gap Closure Mode) and @Tibsfox (test suite covering file existence,
section structure, and agent wiring).
- 5 reference files in get-shit-done/references/ — each with named reasoning
models, Counters annotations, Conflict Resolution sequencing, and When NOT
to Think guidance
- Inline @-reference wiring placed inside the specific step/section blocks
where thinking decisions occur (not at top-of-agent)
- Planning cluster includes Gap Closure Mode root-cause check section
- Test suite: 63 tests covering file existence, named models, Conflict
Resolution sections, Gap Closure Mode, and inline wiring placement
Closes#1722
Co-authored-by: Tibsfox <tibsfox@users.noreply.github.com>
Co-authored-by: Rezolv <davesienkowski@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Combines implementation by @Tibsfox (test suite, 80% fuzzy threshold)
and @davesienkowski (must_have schema, mandatory audit fields, full
lifecycle with re-verification carryforward and overrides_applied counter,
embedded verifier step 3b, When-NOT-to-use guardrails).
- New reference: get-shit-done/references/verification-overrides.md
with must_have/accepted_by/accepted_at schema, 80% fuzzy match
threshold, When to Use / When NOT to Use guardrails, full override
lifecycle (re-verification carryforward, milestone audit surfacing)
- gsd-verifier.md updated with required_reading block, embedded Step 3b
override check before FAIL marking, and overrides_applied frontmatter
- 27-assertion test suite covering reference structure, field names,
threshold value, lifecycle fields, and agent cross-reference
Closes#1747
Co-authored-by: Tibsfox <tibsfox@users.noreply.github.com>
Co-authored-by: Rezolv <davesienkowski@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: replace /gsd: command format with /gsd- skill format in all suggestions
All next-step suggestions shown to users were still using the old colon
format (/gsd:xxx) which cannot be copy-pasted as skills. Migrated all
occurrences across agents/, commands/, get-shit-done/, docs/, README files,
bin/install.js (hardcoded defaults for claude runtime), and
get-shit-done/bin/lib/*.cjs (generate-claude-md templates and error messages).
Updated tests to assert new hyphen format instead of old colon format.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: migrate remaining /gsd: format to /gsd- in hooks, workflows, and sdk
Addresses remaining user-facing occurrences missed in the initial migration:
- hooks/: fix 4 user-facing messages (pause-work, update, fast, quick)
and 2 comments in gsd-workflow-guard.js
- get-shit-done/workflows/: fix 21 Skill() literal calls that Claude
executes directly (installer does not transform workflow content)
- sdk/prompt-sanitizer.ts: update regex to strip /gsd- format in addition
to legacy /gsd: format; update JSDoc comment
- tests/: update autonomous-ui-steps, prompt-sanitizer to assert new format
Note: commands/gsd/*.md frontmatter (name: gsd:xxx) intentionally unchanged
— installer derives skillName from directory path, not the name field.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(plan-phase): preserve --chain flag in auto-advance sync and handle ui-phase gate in chain mode
Bug 1: step 15 sync-flag check only guarded against --auto, causing
_auto_chain_active to be cleared when plan-phase is invoked without
--auto in ARGUMENTS even though a --chain pipeline was active. Added
--chain to the guard condition, matching discuss-phase behaviour.
Bug 2: UI Design Contract gate (step 5.6) always exited the workflow
when UI-SPEC was missing, breaking the discuss --chain pipeline
silently. When _auto_chain_active is true, the gate now auto-invokes
gsd-ui-phase --auto via Skill() and continues to step 6 without
prompting. Manual invocations retain the existing AskUserQuestion flow.
* fix: remove <sub>/clear</sub> pattern and duplicate old-format command in discuss-phase.md
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The gsd-verifier was reporting false-positive gaps for items explicitly
scheduled in later phases of the milestone (e.g., reporting a Phase 5
item as a gap during Phase 1 verification). This adds Step 9b to
cross-reference gaps against later phases using `roadmap analyze` and
move matched items to a `deferred` list that does not affect status.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* chore: add v1.31.0 npm known-issue notice to issue template config
Adds a top-priority contact link to the issue template chooser so users
are redirected to the Discussions announcement before opening a duplicate
issue about v1.31.0 not being on npm.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(phase-runner): add research gate to block planning on unresolved open questions (#1602)
Plan-phase could proceed to planning even when RESEARCH.md had unresolved
open questions in its ## Open Questions section. This caused agents to
plan and execute with fundamental design decisions still undecided.
- Add `research-gate.ts` with pure `checkResearchGate()` function that
parses RESEARCH.md for unresolved open questions
- Integrate gate into PhaseRunner between research (step 2) and plan
(step 3) using existing `invokeBlockerCallback` pattern
- Add Dimension 11 (Research Resolution) to gsd-plan-checker.md agent
- Gate passes when: no Open Questions section, section has (RESOLVED)
suffix, all individual questions marked RESOLVED, or section is empty
- Gate fires `onBlockerDecision` callback with PhaseStepType.Research
and lists the unresolved questions in the error message
- Auto-approves (skip) when no callback registered (headless mode)
- 18 new tests: 13 unit tests for checkResearchGate, 5 integration
tests for PhaseRunner research gate behavior
Closes#1602
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: add failing tests for planner modular decomposition
- Assert gsd-planner.md is under 45K after extraction (currently ~50K)
- Assert three reference files exist (gap-closure, revision, reviews)
- Assert planner contains reference pointers to each extracted file
- Assert each reference file contains key content from the original mode
* feat(agents): modular decomposition of gsd-planner.md to fix 50K char limit
Extracts three non-standard mode sections from gsd-planner.md into dedicated
reference files loaded on-demand, and calibrates the security scanner to use
a per-file-type threshold (100K for agent source files vs 50K for user input).
Structural changes:
- Extract <gap_closure_mode> → get-shit-done/references/planner-gap-closure.md
- Extract <revision_mode> → get-shit-done/references/planner-revision.md
- Extract <reviews_mode> → get-shit-done/references/planner-reviews.md
- Add <load_mode_context> step in execution_flow (conditional lazy loading)
- gsd-planner.md: 50,112 → 45,352 chars (well under new 45K target)
Security scanner fix:
- Split agent file check: injection patterns (unchanged) + separate 100K size limit
- The 50K strict-mode limit was designed for user-supplied input, not trusted source files
- Agent files still have a size guard to catch accidental bloat
Partially addresses #1495
* fix(tests): normalize CRLF before measuring planner file size
Windows git checkouts add \r per line, inflating String.length by ~1150 chars
for a 1,400-line file. The 45K threshold test failed on windows-latest because
45,352 chars (Linux) became 46,507 chars (Windows). Apply the same CRLF
normalization pattern used in tests/reachability-check.test.cjs.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(planner): add reachability_check step to prevent unreachable code
Closes#1495
* fix: trim gsd-planner.md below 50000-char limit after rebase
The reachability_check addition pushed the file to 50,275 chars when
merged with the assign_waves additions from #1600. Condense both sections
while preserving all logic; file is now 49,859 chars.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(security): normalize CRLF before prompt-stuffing length check
On Windows, git checks out files with CRLF line endings. JavaScript's
String.length counts \r characters, so a 49,859-byte file measures as
51,126 chars on Windows — falsely tripping the 50,000-char security
scanner. Normalize CRLF → LF before measuring in security.cjs and in
the reachability-check test.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: trim gsd-planner.md to stay under 50000-char limit after merge with main
After rebasing onto main (which added mcp_tool_usage block), combined content
reached 50031 chars. Remove suggested log format from assign_waves rule to
bring file to 49972 chars, well under the 50000-char security scanner limit.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(agents): explicitly instruct agents to use available MCP tools
GSD executor and planner agents were not mentioning available MCP servers
in their task instructions, causing subagents to skip Context7 and other
configured MCP tools even when available.
Closes#1388
* fix(tests): make copilot executor tool assertion dynamic
Hardcoded tools: ['read', 'edit', 'execute', 'search'] assertion broke
when mcp__context7__* was added to gsd-executor.md frontmatter. Replace
with per-tool presence checks so adding new tools never breaks the test.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
When Playwright-MCP is available in the session, GSD UI verification
steps can be automated via screenshot comparison instead of manual
checkbox review. Falls back to manual flow when Playwright is not
configured.
Closes#1420
* fix: correct STATE.md progress counter fields during plan/phase completion (#1589)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* ci: re-run CI with Windows pointer lifecycle fix in main
* fix: orchestrator owns STATE.md/ROADMAP.md writes in parallel worktree mode (#1571)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: detect files_modified overlap and enforce wave ordering for dependent plans (#1587)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: trim gsd-planner.md below 50000-char prompt-injection limit
The assign_waves section added in this branch pushed agents/gsd-planner.md
to 50271 chars, triggering the security scanner's prompt-stuffing check on
all CI platforms. Condense prose while preserving all logic and validation
rules; file is now 49754 chars.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
permissionMode: acceptEdits in gsd-executor and gsd-debugger frontmatter
is Claude Code-specific and causes Gemini CLI to hard-fail on agent load
with "Unrecognized key(s) in object: 'permissionMode'". The field also
has no effect in Claude Code (subagent Write permissions are controlled
at runtime level regardless). Remove it from both agents and update
tests to enforce cross-runtime compatibility.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(01-02): complete gsd-doc-writer agent skeleton plan
- SUMMARY.md for plan 01-02
- STATE.md advanced to plan 2/2, progress 50%
- ROADMAP.md updated with phase 1 plan progress
- REQUIREMENTS.md marked DOCG-01 and DOCG-08 complete
* feat(01-01): create lib/docs.cjs with cmdDocsInit and detection helpers
- Add cmdDocsInit following cmdInitMapCodebase pattern
- Add hasGsdMarker(), scanExistingDocs(), detectProjectType()
- Add detectDocTooling(), detectMonorepoWorkspaces() private helpers
- GSD_MARKER constant for generated-by tracking
- Only Node.js built-ins and local lib requires used
* feat(01-01): wire docs-init into gsd-tools.cjs and register gsd-doc-writer model profile
- Add const docs = require('./lib/docs.cjs') to gsd-tools.cjs
- Add case 'docs-init' routing to docs.cmdDocsInit
- Add docs-init to help text and JSDoc header
- Register gsd-doc-writer in MODEL_PROFILES (quality:opus, balanced:sonnet, budget:haiku)
- Fix docs.cjs: inline withProjectRoot logic via checkAgentsInstalled (private in init.cjs)
* docs(01-01): complete docs-init command plan
- SUMMARY.md documenting cmdDocsInit, detection helpers, wiring
- STATE.md advanced, progress updated to 100%
- ROADMAP.md phase 1 marked Complete
- REQUIREMENTS.md INFRA-01, INFRA-02, CONS-03 marked complete
* feat(01-02): create gsd-doc-writer agent skeleton
- YAML frontmatter with name, description, tools, color: purple
- role block with doc_assignment receiving convention
- create_mode and update_mode sections
- 9 stub template sections (readme, architecture, getting_started, development, testing, api, configuration, deployment, contributing)
- Each template has Required Sections list and Phase 3 TODO
- critical_rules prohibiting GSD methodology and CHANGELOG
- success_criteria checklist
- No GSD methodology leaks in template sections
* feat(02-01): add docs-update workflow Steps 1-6 — init, classify, route, resolve, detect
- init_context step calling docs-init with @file: handling and agent-skills loading
- validate_agents step warns on missing gsd-doc-writer without halting
- classify_project step maps project_type signals to 5 primary labels plus conditional docs
- build_doc_queue step with always-on 6 docs and conditional API/CONTRIBUTING/DEPLOYMENT routing
- resolve_modes step with doc-type to canonical path mapping and create/update detection
- detect_runtime_capabilities step with Task tool detection and sequential fallback routing
* docs(02-01): complete docs-update workflow plan — 13-step orchestration for parallel doc generation
- 02-01-SUMMARY.md: plan results, decisions, file inventory
- STATE.md: advanced to last plan, progress 100%, decisions recorded
- ROADMAP.md: Phase 2 marked Complete (1/1 plans with summary)
- REQUIREMENTS.md: marked INFRA-04, DOCG-03, DOCG-04, CONS-01, CONS-02, CONS-04 complete
* docs(03-02): complete command entry point and workflow extension plan
- 03-02-SUMMARY.md: plan results, decisions, file inventory
- STATE.md: advanced to plan 2, progress 100%, decisions recorded
- ROADMAP.md: Phase 3 marked Complete (2/2 plans with summaries)
- REQUIREMENTS.md: marked INFRA-03, EXIST-01, EXIST-02, EXIST-04 complete
* feat(03-01): fill all 9 doc templates, add supplement mode and per-package README template
- Replace all 9 template stubs with full content guidance (Required Sections, Content Discovery, Format Notes)
- Add shared doc_tooling_guidance block for Docusaurus, VitePress, MkDocs, Storybook routing
- Add supplement_mode block: append-only strategy with heading comparison and safety rules
- Add template_readme_per_package for monorepo per-package README generation
- Update role block to list supplement as third mode; add rule 7 to critical_rules
- Add supplement mode check to success_criteria
- Remove all Phase 3 TODO stubs and placeholder comments
* feat(03-02): add docs-update command entry point with --force and --verify-only flags
- YAML frontmatter with name, argument-hint, allowed-tools
- objective block documents flag semantics with literal-token enforcement pattern
- execution_context references docs-update.md workflow
- context block passes $ARGUMENTS and documents flag derivation rules
- --force takes precedence over --verify-only when both present
* feat(03-02): extend docs-update workflow with preservation_check, monorepo dispatch, and verify-only
- preservation_check step between resolve_modes and detect_runtime_capabilities
- preservation_check skips on --force, --verify-only, or no hand-written docs
- per-file AskUserQuestion choice: preserve/supplement/regenerate with fallback default to preserve
- dispatch_monorepo_packages step after collect_wave_2 for per-package READMEs
- verify_only_report early-exit step with VERIFY marker count and Phase 4 deferral message
- preservation_mode field added to all doc_assignment blocks in dispatch_wave_1, dispatch_wave_2
- sequential_generation extended with monorepo per-package section
- commit_docs updated to include per-package README files pattern
- report extended with per-package README rows and preservation decisions
- success_criteria updated with preservation, --force, --verify-only, and monorepo checks
* feat(04-01): create gsd-doc-verifier agent with claim extraction and filesystem verification
- YAML frontmatter with name, description, tools, and color fields
- claim_extraction section with 5 categories: file paths, commands, API endpoints, functions, dependencies
- skip_rules section for VERIFY markers, placeholders, example prefixes, and diff blocks
- verification_process with 6 steps using filesystem tools only (no self-consistency checks)
- output_format with exact JSON shape per D-01
- critical_rules enforcing filesystem-only verification and read-only operation
* feat(04-01): add fix_mode to gsd-doc-writer with surgical correction instructions
- Add fix_mode section after supplement_mode in modes block
- Document fix mode as valid option in role block mode list
- Add failures field to doc_assignment fields (fix mode only)
- fix_mode enforces surgical precision: only correct listed failing lines
- VERIFY marker fallback when correct value cannot be determined
* test(04-03): add docs-init integration test suite
- 13 tests across 4 describe blocks covering JSON output shape, project type
detection, existing doc scanning, GSD marker detection, and doc tooling
- Tests use node:test + node:assert/strict with beforeEach/afterEach lifecycle
- All 13 tests pass with `node --test tests/docs-update.test.cjs`
* feat(04-02): add verify_docs, fix_loop, scan_for_secrets steps to docs-update workflow
- verify_docs step spawns gsd-doc-verifier per generated doc and collects structured JSON results
- fix_loop step bounded at 2 iterations with regression detection (D-05/D-06)
- scan_for_secrets step uses exact map-codebase grep pattern before commit (D-07/D-08)
- verify_only_report updated to invoke real gsd-doc-verifier instead of VERIFY marker count stub
- success_criteria updated with 4 new verification gate checklist items
* docs(04-02): complete verification gate workflow steps plan
- SUMMARY.md: verify_docs, fix_loop, scan_for_secrets, and updated verify_only_report
- STATE.md: advanced to ready_for_verification, 100% progress, decisions logged
- ROADMAP.md: phase 4 marked Complete (3/3 plans with SUMMARYs)
- REQUIREMENTS.md: VERF-01, VERF-02, VERF-03 all marked complete
* refactor(profiles): Adds 'gsd-doc-verifier' to the 'MODEL_PROFILES'
* feat(agents): Add critical rules for file creation and update install test
* docs(05): create phase plan for docs output refinement
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(05-01): make scanExistingDocs recursive into docs/ subdirectories
- Replace flat docs/ scan with recursive walkDir helper (MAX_DEPTH=4)
- Add SKIP_DIRS filtering at every level of recursive walk
- Add fallback to documentation/ or doc/ when docs/ does not exist
- Update JSDoc to reflect recursive scanning behavior
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(05-01): update gsd-doc-writer default path guidance to docs/
- Change "No tooling detected" guidance to default to docs/ directory
- Add README.md and CONTRIBUTING.md as root-level exceptions
- Add instruction to create docs/ directory if it does not exist
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(05-02): invert path table to default docs to docs/ directory
- Invert resolve_modes path table: docs/ is primary for all types except readme and contributing
- Add mkdir -p docs/ instruction before agent dispatch
- Update all downstream path references: collect_wave_1, collect_wave_2, commit_docs, report, verify tables
- Update sequential_generation wave_1_outputs and resolved path references
- Update success criteria and verify_only_report examples to use docs/ paths
* feat(05-02): add CONTRIBUTING confirmation gate and existing doc review queue
- Add CONTRIBUTING.md user confirmation prompt in build_doc_queue (skipped with --force or when file exists)
- Add review_queue for non-canonical existing docs (verification only, not rewriting)
- Add review_queue verification in verify_docs step with fix_loop exclusion
- Add existing doc accuracy review section to report step with manual correction guidance
* docs(05-02): complete path table inversion and doc queue improvements plan
- Add 05-02-SUMMARY.md with execution results
- Update STATE.md with position, decisions, and metrics
- Update ROADMAP.md with phase 05 plan progress
* fix(05): replace plain text y/n prompts with AskUserQuestion in docs-update workflow
Three prompts were using plain text (y/n) instead of GSD's standard
AskUserQuestion pattern: CONTRIBUTING.md confirmation, doc queue
proceed gate, and secrets scan confirmation.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(05): structure-aware paths, non-canonical doc fixes, and gap detection
- resolve_modes now inspects existing doc directory structure and places
new docs in matching subdirectories (e.g., docs/architecture/ if that
pattern exists), instead of dumping everything flat into docs/
- Non-canonical docs with inaccuracies are now sent to gsd-doc-writer
in fix mode for surgical corrections, not just reported
- Added documentation gap detection step that scans the codebase for
undocumented areas and prompts user to create missing docs
- Added type: custom support to gsd-doc-writer with template_custom
section for gap-detected documentation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(05): smarter structure-aware path resolution for grouped doc directories
When a project uses grouped subdirectories (docs/architecture/,
docs/api/, docs/guides/), ALL canonical docs must be placed in
appropriate groups — none left flat in docs/. Added resolution
chain per doc type with fallback creation. Filenames now match
existing naming style (lowercase-kebab vs UPPERCASE). Queue
presentation shows actual resolved paths, not defaults.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(05): restore mode resolution table as primary queue presentation
The table showing resolved paths, modes, and sources for each doc
must be displayed before the proceed/abort confirmation. It was
replaced by a simple list — now restored as the canonical queue view.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(05): use table format for existing docs review queue presentation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(05): add work manifest for structured handoffs between workflow steps
Root cause from smoke test: orchestrator forgot to verify 45 non-canonical
docs because the review_queue had no structural scaffolding — it existed
only in orchestrator memory. Fix:
1. Write docs-work-manifest.json to .planning/tmp/ after resolve_modes
with all canonical_queue, review_queue, and gap_queue items
2. Every subsequent step (dispatch, collect, verify, fix_loop, report)
MUST read the manifest first — single source of truth
3. Restructured verify_docs into explicit Phase 1 (canonical) and
Phase 2 (non-canonical) with separate dispatch for each
4. Both queues now eligible for fix_loop corrections
5. Added manifest read instructions to all dispatch/collect steps
Follows the same pattern as execute-phase's phase-plan-index for
tracking work items across multi-step orchestration.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(05): update workflow purpose to reflect full command scope
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor(05): remove redundant steps from docs-update workflow
- Remove validate_agents step (if command is available, agents are installed)
- Remove agents_installed/missing_agents extraction from init_context
- Remove available_agent_types block (agent types specified in each Task call)
- Remove detect_runtime_capabilities step (runtime knows its own tools)
- Replace hardcoded flat paths in collect_wave_1/2 with manifest resolved_paths
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(05): restore available_agent_types section required by test suite
Test enforces that workflows spawning named agents must declare them
in an <available_agent_types> block. Added back with both gsd-doc-writer
and gsd-doc-verifier listed.
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 phases have many user decisions, the planner sometimes silently
simplifies them (e.g., "D-26: calculated costs" becomes "static labels v1")
instead of delivering what the user decided. This causes downstream
execution to build the wrong thing.
Three changes prevent this:
1. **gsd-planner.md** — `<scope_reduction_prohibition>` section:
- Prohibits language like "v1", "static for now", "future enhancement"
- Requires decision coverage matrix mapping every D-XX to a task
- When phase is too complex: return PHASE SPLIT RECOMMENDED instead
of simplifying decisions
2. **gsd-plan-checker.md** — Dimension 7b: Scope Reduction Detection:
- Scans task actions for scope reduction patterns
- Cross-references with CONTEXT.md to verify full delivery
- Always BLOCKER severity (never warning)
- Includes real-world example from production incident
3. **plan-phase.md** — Step 9b: Handle Phase Split:
- New flow when planner returns PHASE SPLIT RECOMMENDED
- Three options: Split / Proceed anyway / Prioritize
- User decides which decisions are "now" vs "later"
Root cause: planner's instinct when facing complexity is to simplify
individual requirements. Correct behavior is to split the phase so
every decision is implemented at full fidelity.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Research agents must now tag every factual claim with its source:
[VERIFIED], [CITED], or [ASSUMED]. An Assumptions Log section in
RESEARCH.md collects all [ASSUMED] claims so downstream agents and
users can identify decisions that need confirmation before execution.
Prevents unvalidated assumptions (e.g. "audit logs should be permanent")
from propagating unchallenged through research → planning → execution.
Closes#1431
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The verifier's Step 2 previously used Option A (PLAN frontmatter
must_haves) exclusively when present, skipping Option B (ROADMAP SCs).
This allowed planners to define a subset of must_haves, silently
bypassing roadmap Success Criteria verification.
Now ROADMAP SCs are always loaded first (Step 2a), PLAN must_haves
are merged on top (Step 2b), and a merge step (Step 2c) ensures
plan-authored must_haves can add but never subtract from the roadmap
contract.
Addresses #1418 (Gap 2)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The verifier agent could set status: passed even when the report contained
a non-empty "Human Verification Required" section. This bypassed the
human_needed → HUMAN-UAT.md → user approval gate, allowing phases to be
marked complete without human testing.
Replace the advisory status descriptions with an ordered decision tree
(most restrictive first): gaps_found → human_needed → passed. The passed
status is now only valid when zero human verification items exist.
Synced the same decision tree in the verify-phase workflow.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
gsd-tools detects plan files by matching the glob `*-PLAN.md`
(e.g. 01-01-PLAN.md). When the planner generates files using a
different convention — wave-based names, wrong prefix order, or
lowercase — the tool returns plan_count: 0 and execution cannot
proceed.
Root cause: the write_phase_prompt step only said
"Write to .../XX-name/{phase}-{NN}-PLAN.md" — ambiguous enough
for the agent to produce PLAN-01-auth.md, 01-PLAN-01.md, etc.
Observed across real usage (306 sessions analyzed):
- Phases 2, 3, 4: plan files used wave-based names instead of the
numeric format gsd-tools expects; required manual detection and
adaptation before execution could proceed each time
- gsd-tools roadmap get-phase failed on Phase 3 due to format
mismatch; Claude fell back to parsing ROADMAP.md manually
- Naming mismatch caused friction in at least 4 separate sessions,
each requiring a manual workaround
Fix: add a CRITICAL naming block in write_phase_prompt with the
exact required pattern, component definitions, correct/incorrect
examples, and explicit ❌ markers for variants that break detection.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- gsd-security-auditor.md: replace <threat_register> with <threat_model>
(stale tag name inconsistent with every other file in the PR)
- verify-work.md: parse threats_open from SECURITY.md frontmatter when
file exists; block if > 0, matching execute-phase.md gate logic
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Address 4 root causes of Windows + Claude Code reliability issues:
1. Workflow shell robustness: add || true guards to informational commands
(ls, grep, find, cat) that return non-zero on "no results", preventing
workflow step failures under strict execution models. Guard glob loops
with [ -e "$var" ] || continue to handle empty glob expansion.
2. Hook stdin handling: replace readFileSync('/dev/stdin') with async
process.stdin + timeout in agent templates (gsd-verifier.md). Existing
JS hooks already have timeout guards.
3. project_root detection: fix isInsideGitRepo() to check .git at the
candidate parent level (not just below it), enabling correct detection
when .git and .planning/ are siblings at the same directory level —
the common single-repo case from a subdirectory.
4. @file: handoff: add missing @file: handlers to autonomous.md and
manager.md workflows that call gsd-tools init but lacked the handler
for large output payloads.
Fixes#1343
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Worktree agents (gsd-executor, gsd-debugger) prompt for edit permissions
on every new directory they touch, even when the user has "accept edits"
enabled. This is caused by Claude Code's directory-scoped permission
model not propagating to worktree paths.
Setting permissionMode: acceptEdits in the agent frontmatter tells Claude
Code to auto-approve file edits for these agents, bypassing the per-
directory prompts. This is safe because these agents are already granted
Write/Edit in their tools list and are spawned in isolated worktrees.
- Add permissionMode: acceptEdits to gsd-executor.md frontmatter
- Add permissionMode: acceptEdits to gsd-debugger.md frontmatter
- Add regression tests verifying worktree agents have the field
- Add test ensuring all isolation="worktree" spawns are covered
Upstream: anthropics/claude-code#29110, anthropics/claude-code#28041
Fixes#1334
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add UI keyword detection list for identifying frontend-heavy phases
- Roadmapper annotates phases with **UI hint**: yes when keywords match
- Annotation consumed by downstream workflows to suggest /gsd:ui-phase
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add codebase-first assumption-driven alternative to the interview-style
discuss-phase. New `workflow.discuss_mode: "assumptions"` config routes
to a separate workflow that spawns a gsd-assumptions-analyzer agent to
read 5-15 codebase files, surface assumptions with evidence, and ask
only for corrections (~2-4 interactions vs ~15-20).
- New gsd-assumptions-analyzer agent for deep codebase analysis
- New discuss-phase-assumptions.md workflow (15 steps)
- Command-level routing via dual @reference + process gate
- Identical CONTEXT.md output — downstream agents unaffected
- Existing discuss-phase.md workflow untouched (zero diff)
- Mode-aware plan-phase gate and progress display
- User documentation and integration tests
- Update agent count and list in copilot-install tests (17 → 18)
Closes#637
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
