The summary template writes task count as `**Tasks:** N` in the
Performance section, but `cmdMilestoneComplete` only counted
`## Task N` markdown headers — which don't exist in that format.
Now checks three patterns in order: `**Tasks:** N` field (primary),
`<task` XML tags, then `## Task N` headers (legacy fallback).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Prevent silent loss of UAT/verification items when projects advance.
Surfaces outstanding items across all prior phases so nothing is forgotten.
New command:
- /gsd:audit-uat — cross-phase audit with categorized report and test plan
New capabilities:
- Cross-phase health check in /gsd:progress (Step 1.6)
- status: partial for incomplete UAT sessions
- result: blocked with blocked_by tag for dependency-gated tests
- human_needed items persisted as trackable HUMAN-UAT.md files
- Phase completion and transition warnings for verification debt
Files: 4 new, 14 modified (9 feature + 5 docs)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three commands reimplemented from positively-received community PRs:
1. /gsd:review (#925) — Cross-AI peer review
Invoke external AI CLIs (Gemini, Claude, Codex) to independently
review phase plans. Produces REVIEWS.md with per-reviewer feedback
and consensus summary. Feed back into planning via --reviews flag.
Multiple users praised the adversarial review concept.
2. /gsd:plant-seed (#456) — Forward-looking idea capture
Capture ideas with trigger conditions that auto-surface during
/gsd:new-milestone. Seeds preserve WHY, WHEN to surface, and
breadcrumbs to related code. Better than deferred items because
triggers are checked, not forgotten.
3. /gsd:pr-branch (#470) — Clean PR branches
Create a branch for pull requests by filtering out .planning/
commits. Classifies commits as code-only, planning-only, or mixed,
then cherry-picks only code changes. Reviewers see clean diffs.
All three are standalone command+workflow additions with no core code
changes. Help workflow updated. Test skill counts updated.
797/797 tests pass.
Node 18 reached EOL April 2025. Node 24 is the current LTS target.
Changes:
- CI matrix: [18, 20, 22] → [20, 22, 24]
- package.json engines: >=16.7.0 → >=20.0.0
- Removed Node 18 conditional in CI (c8 coverage works on all 20+)
- Simplified CI to single test:coverage step for all versions
797/797 tests pass on Node 24.
Consolidates repeated path.join(cwd, '.planning', ...) patterns into
calls to the shared planningPaths() helper from core.cjs.
Modules updated:
- state.cjs: 16 → planningPaths() (2 remain for non-standard paths)
- commands.cjs: 8 → planningPaths() (4 remain for todos dir)
- milestone.cjs: 5 → planningPaths() (3 remain for archive/milestones)
- roadmap.cjs: 4 → planningPaths()
Benefits:
- Single source of truth for .planning/ directory structure
- Easier to change planning dir location in the future
- Consistent path construction across the codebase
- No behavioral changes — pure refactor
797/797 tests pass.
When GSD installs codex_hooks = true under [features], any non-boolean
keys already in that section (e.g. model = "gpt-5.4") cause Codex's
TOML parser to fail with 'invalid type: string, expected a boolean'.
Root cause: TOML sections extend until the next [section] header. If
the user placed model/model_reasoning_effort under [features] (common
since Codex's own config format encourages this), GSD's installer
didn't detect or correct the structural issue.
Fix: After injecting codex_hooks, scan the [features] section for
non-boolean values and move them above [features] to the top level.
This preserves the user's keys while keeping [features] clean for
Codex's strict boolean parser.
Includes 2 regression tests:
- Detects non-boolean keys under [features] (model, model_reasoning_effort)
- Confirms boolean keys (codex_hooks, multi_agent) are not flagged
Closes#1202
gsd-check-update.js scanned ALL .js files in the hooks directory and
flagged any without a gsd-hook-version header as stale. This incorrectly
flagged user-created hooks (e.g. guard-edits-outside-project.js),
producing a persistent 'stale hooks' warning that /gsd:update couldn't
resolve.
Fix: filter hookFiles to f.startsWith('gsd-') && f.endsWith('.js')
since all GSD hooks follow the gsd-* naming convention.
Includes regression test validating the filter excludes user hooks.
Closes#1200
Tests expected 39 skill folders but got 42 after adding add-backlog,
review-backlog, and thread commands. Updated both the hardcoded count
and EXPECTED_SKILLS constant.
Three new commands for managing ideas and cross-session context:
/gsd:add-backlog <description>
Adds a 999.x numbered backlog item to ROADMAP.md. Creates phase directory
immediately so /gsd:discuss-phase and /gsd:plan-phase work on them.
No dependencies, no sequencing — pure parking lot.
/gsd:review-backlog
Lists all 999.x items, lets user promote to active milestone, keep, or
remove. Promotion renumbers to next sequential phase with proper deps.
/gsd:thread [name | description]
Three modes:
- No args: list all threads with status
- Existing name: resume thread, load context
- New description: create thread from current conversation context
Threads live in .planning/threads/ as lightweight markdown files with
Goal, Context, References, and Next Steps sections.
Design:
- Self-contained command files, no core changes needed
- 999.x numbering keeps backlog out of active sequence
- Threads are independent of phases — cross-session knowledge stores
- Both features compose with existing GSD commands
Fixes#1005
Adds workflow.research_questions config toggle (default: false) that
enables web research before asking questions during /gsd:new-project
and /gsd:discuss-phase.
When enabled:
- discuss-phase: searches best practices for each gray area before
presenting questions, showing 2-3 bullet points of findings
- new-project: researches the user's described domain before asking
follow-up questions, weaving findings into the conversation
Added to /gsd:settings as a toggle ('Research Qs' section).
Closes#1186
* fix: universal agent name replacement for non-Claude runtimes (#766)
Adds neutralizeAgentReferences() shared function that all non-Claude
runtime converters call to replace Claude-specific references:
- 'Claude' (standalone agent name) → 'the agent'
- 'CLAUDE.md' → runtime-specific file (AGENTS.md, GEMINI.md, COPILOT.md)
- Removes 'Do NOT load full AGENTS.md' (harmful for AGENTS.md runtimes)
Preserves: 'Claude Code' (product), 'Claude Opus/Sonnet/Haiku' (models),
'claude-' prefixes (packages, CSS classes).
Integrated into: OpenCode, Gemini, Copilot, Antigravity, and Codex
converters. Claude Code converter unchanged (references are correct).
Includes 7 new tests covering all replacement rules.
Closes#766
* fix: use copilot-instructions.md instead of COPILOT.md for Copilot runtime
Addresses review from Solvely-Colin: Copilot's actual instruction file
is copilot-instructions.md, not COPILOT.md. The neutralizer was mapping
CLAUDE.md -> COPILOT.md which would reference a non-existent file.
- install.js: pass 'copilot-instructions.md' to neutralizeAgentReferences
- runtime-converters.test.cjs: update test to validate correct filename
New opt-in PreToolUse hook that warns when Claude edits files outside
a GSD workflow context (no active /gsd: command or subagent).
Soft guard — advises, does not block. The edit proceeds but Claude
sees a reminder to use /gsd:fast or /gsd:quick for state tracking.
Enable: set hooks.workflow_guard: true in .planning/config.json
Default: disabled (false)
Allows without warning:
- .planning/ files (GSD state management)
- Config files (.gitignore, .env, CLAUDE.md, settings.json)
- Subagent contexts (executor, planner, etc.)
Includes 3s stdin timeout guard and silent fail-safe.
Closes#678
Code review fixes from codebase pattern analysis:
1. state.cjs: Remove duplicate stateExtractField() definition (lines 12 vs 184).
The second definition shadowed the first with identical logic. Keeps the
original that uses escapeRegex() from core.cjs.
2. init.cjs: Replace Unix-only 'find' pipe with cross-platform fs.readdirSync
recursive walk for code file detection. The execSync('find ... | grep ...')
command fails on Windows where these Unix utilities aren't available.
Removes unused child_process import.
3. state.cjs: Add lockfile-based mutual exclusion to writeStateMd() to prevent
parallel executor agents from overwriting each other's STATE.md changes.
Uses O_EXCL atomic file creation for lock acquisition, stale lock detection
(10s timeout), and spin-wait with jitter. Ensures data integrity during
wave-based parallel execution where multiple agents update STATE.md
concurrently.
All 755 existing tests pass.
New lightweight command for tasks too small to justify planning overhead:
typo fixes, config changes, forgotten commits, simple additions.
- Runs inline in current context (no subagent spawn)
- No PLAN.md or SUMMARY.md generated
- Scope guard: redirects to /gsd:quick if task needs >3 file edits
- Atomic commit with conventional commit format
- Logs to STATE.md quick tasks table if present
Complements /gsd:quick (which spawns planner+executor) for cases where
the planning overhead exceeds the actual work.
Closes#609
Windows users experience plan-phase freezes due to Claude Code stdio
deadlocks with MCP servers. When a subagent hangs, the orchestrator
blocks indefinitely with no timeout or error.
Adds:
- Windows troubleshooting section to plan-phase.md with:
- Orphaned process cleanup (PowerShell commands)
- Stale task directory cleanup (~/.claude/tasks/)
- MCP server reduction advice
- --skip-research fallback to reduce agent chain
- Stale task directory detection to health.md (I002 diagnostic)
- Reports count of stale dirs on --repair
- Safe cleanup guidance
Closes#732
Adds --analyze flag to /gsd:discuss-phase that provides a trade-off
analysis before each question (or question group in --batch mode).
When active, each question is preceded by:
- 2-3 options with pros/cons based on codebase context
- A recommended approach with reasoning
- Known pitfalls or constraints from prior phases
Composable with existing flags: --batch --analyze gives grouped
questions each with trade-off tables.
Closes#833
Updates all docs to reflect v1.26.0 features and changes:
README.md:
- Add /gsd:ship and /gsd:next to command tables
- Add /gsd:session-report to Session section
- Update workflow to show ship step and auto-advance
- Update inherit profile description for non-Anthropic providers
docs/COMMANDS.md:
- Add /gsd:next command reference with full state detection logic
- Add /gsd:session-report command reference with report contents
docs/FEATURES.md:
- Add Auto-Advance (Next) feature (#14)
- Add Cross-Phase Regression Gate feature (#20)
- Add Requirements Coverage Gate feature (#21)
- Add Session Reporting feature (#24)
- Fix all section numbering (was broken with duplicates)
- Update inherit profile to mention non-Anthropic providers
- Renumber all 39 features consistently
docs/USER-GUIDE.md:
- Add /gsd:ship to workflow diagram
- Add /gsd:next and /gsd:session-report to command tables
- Add HANDOFF.json and reports/ to file structure
- Add troubleshooting for non-Anthropic model providers
- Add recovery entries for session-report and next
- Update example workflow to include ship and session-report
docs/CONFIGURATION.md:
- Update inherit profile to mention non-Anthropic providers
Keep `/gsd-*` command examples slash-prefixed during Cursor conversion while still normalizing legacy `gsd:` syntax, and add regression coverage for Next Up markdown output.
Made-with: Cursor
Prevent Cursor from treating frontmatter quotes as part of skill/subagent identifiers by emitting plain name scalars, and add regression tests to lock the conversion behavior.
Made-with: Cursor
