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.
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
* 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 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
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
Add a cross_reference_todos step to discuss-phase that surfaces relevant
backlog items before scope-setting decisions are made.
Implementation:
- New 'todo match-phase <N>' CLI command (commands.cjs) that scores
pending todos against a phase's ROADMAP goal using three heuristics:
keyword overlap, area match, and file path overlap
- New cross_reference_todos step in discuss-phase.md between
load_prior_context and scout_codebase
- CONTEXT.md template gains 'Folded Todos' subsection in <decisions>
and 'Reviewed Todos (not folded)' subsection in <deferred>
Design:
- No AI call for matching — pure keyword/area/file heuristics for speed
- Silent skip when todo_count is 0 or no matches (no workflow slowdown)
- Auto mode folds all todos with score >= 0.4 automatically
- Scoring: keywords (up to 0.6), area match (0.3), file overlap (0.4)
Tests: 5 new tests covering empty state, keyword matching, unrelated
todo exclusion, area matching, and score sorting.
Closes#1111
OpenCode does not recognize 'model: inherit' as a valid model identifier —
it throws ProviderModelNotFoundError when spawning any GSD subagent.
Changes:
- Remove 'model: inherit' injection for OpenCode agents in install.js
- Strip 'model:' field entirely during OpenCode frontmatter conversion
(OpenCode uses its configured default model when no model is specified)
- Update tests to verify model: inherit is NOT added
This fixes all 15 GSD agent definitions and the gsd-set-profile command
for OpenCode users.
Fixes#1156
Adds a zero-friction command that detects the current project state and
automatically invokes the next logical workflow step:
- No phases → discuss first phase
- Phase has no context → discuss
- Phase has context but no plans → plan
- Phase has plans but incomplete → execute
- All plans complete → verify and complete phase
- All phases complete → complete milestone
- Paused → resume work
No arguments needed — reads STATE.md, ROADMAP.md, and phase directories
to determine progression. Designed for multi-project workflows.
Closes#927
Previously, calling `mark-complete` on already-completed requirements
reported them as `not_found`, since the regex only matched unchecked
`[ ]` checkboxes and `Pending` table cells.
Now detects `[x]` checkboxes and `Complete` table cells and returns
them in a new `already_complete` array instead of `not_found`.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
PR #1084 added profile-user command and gsd-user-profiler agent but
didn't bump the hardcoded count assertions in copilot-install tests.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add Antigravity runtime support
Add full installation support for the Antigravity AI agent, bringing
get-shit-done capabilities to the new runtime alongside Claude Code,
OpenCode, Gemini, Codex, and Copilot.
- New runtime installation capability in bin/install.js
- Commands natively copied to the unified skills directory
- New test integration suite: tests/antigravity-install.test.cjs
- Refactored copy utility to accommodate Antigravity syntax
- Documentation added into README.md
Co-authored-by: Antigravity <noreply@google.com>
* fix: add missing processAttribution call in copyCommandsAsAntigravitySkills
Antigravity SKILL.md files were written without commit attribution metadata,
inconsistent with the Copilot equivalent (copyCommandsAsCopilotSkills) which
calls processAttribution on each skill's content before writing it.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: update Copilot install test assertions for 3 new UI agents
* docs: update CHANGELOG for Antigravity runtime support
---------
Co-authored-by: Antigravity <noreply@google.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
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>
Add composable --research flag to /gsd:quick that spawns a focused
gsd-phase-researcher before planning. Investigates implementation
approaches, library options, and pitfalls for the task.
Addresses the middle-ground gap between quick (no quality agents) and
full milestone workflows. All three flags are composable:
--discuss --research --full gives the complete quality pipeline.
Made-with: Cursor
Co-authored-by: ralberts3 <ralberts3@gatech.edu>
* perf: make `/gsd:set-profile`'s implementation more programmatic
* perf: run the set-profile script without Claude needing to invoke it
- inject the script's output as dynamic context into the set-profile skill, so that Claude doesn't
need to invoke it and can simply read + print the output to the user
- reference: https://code.claude.com/docs/en/skills#inject-dynamic-context
* feat: improve output message for case where model profile wasn't changed
* feat: specify haiku model for set-profile command since it's so simple
* fix: remove ' (default)' from previousProfile to avoid false negative for didChange
* chore: add docstring to MODEL_PROFILES with note about the analogous markdown reference table
* chore: delete set-profile workflow file that's no longer needed
convertClaudeToOpencodeFrontmatter() was designed for commands but is
also called for agents. For agents it incorrectly strips name: (needed
by OpenCode agents), keeps color:/skills:/tools: (should strip), and
doesn't add model: inherit / mode: subagent (required by OpenCode).
Add isAgent option to convertClaudeToOpencodeFrontmatter() so agent
installs get correct frontmatter: name preserved, Claude-only fields
stripped, model/mode injected. Command conversion unchanged (default).
Includes 14 test cases covering agent and command conversion paths.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Phase numbers reset per milestone (v1.0 Phase 1-26, v1.1 Phase 1-6,
v1.2 Phase 1-6). Functions that searched ROADMAP.md for phase headings
or checkboxes would match archived milestone entries inside <details>
blocks before reaching the current milestone's entries.
This caused:
- roadmap_complete: true for phases that aren't complete (checkbox
regex matched the archived [x] Phase N from a previous milestone)
- phase-complete marking the wrong checkbox (archived instead of current)
- phase-add computing wrong maxPhase from archived headings
- progress not showing phases defined in ROADMAP but not yet on disk
Two bugs caused workflow.research to silently reset to false:
1. new-milestone.md unconditionally overwrote workflow.research via
config-set after asking about research — coupling a per-milestone
decision to a persistent user preference. Now the research question
is per-invocation only; persistent config changes via /gsd:settings.
2. verify.cjs health repair (createConfig/resetConfig) used flat keys
(research, plan_checker, verifier) instead of the canonical nested
workflow object from config.cjs, also missing branch templates,
nyquist_validation, and brave_search fields.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
