Update the `/gsd:review` workflow documentation to include CodeRabbit as
a supported AI reviewer. Clarify that CodeRabbit reviews the current git
diff and may take up to 5 minutes. Update CLI detection and review
process descriptions accordingly.
--full now enables discussion + research + plan-checking + verification.
New --validate flag covers what --full previously did (plan-checking +
verification only). All downstream workflow logic uses $VALIDATE_MODE.
Closes#1498
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When running in --auto or headless mode, the discuss step could loop
indefinitely — each pass reads its own CONTEXT.md, finds "gaps" in
referenced types/interfaces, creates new decisions to fill them, and
repeats. Observed: 34 passes, 167 decisions, 7 hours, zero code written.
Fixes:
- Add max_discuss_passes config (default: 3) to WorkflowConfig
- Add single-pass guard instruction to SDK self-discuss prompt
- Add pass cap documentation to CLI discuss-phase workflow
- Add pass guard step to SDK headless discuss-phase prompt
- Add stall detection note to autonomous workflow
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Executor constraints now prohibit committing docs artifacts (SUMMARY.md,
STATE.md, PLAN.md) — these are the orchestrator's responsibility in
Step 8. Step 8 now explicitly stages all artifacts with git add before
calling gsd-tools commit, and documents that it must always run even if
the executor already committed some files.
This prevents PLAN.md from being left untracked when the executor runs
without worktree isolation (e.g. local repos with no remote, or when
workflow.use_worktrees is false).
Closes#1503
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Executor agents spawned with isolation="worktree" committed to temporary
branches in separate working trees, but no step existed to merge those
changes back or clean up. This left orphan worktrees and unmerged
branches after every execution.
Changes:
- execute-phase.md: add step 4.5 "Worktree cleanup" after wave
completion — merges worktree branch, removes worktree, deletes temp
branch. Handles merge conflicts gracefully.
- quick.md: add worktree cleanup step after executor returns, before
summary verification
- Both workflows skip cleanup when workflow.use_worktrees is false
- Both workflows skip silently when no worktrees are found
Closes#1496
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When discuss-phase is interrupted mid-session (usage limit, crash,
network drop), all user answers were lost — the workflow only wrote
CONTEXT.md and DISCUSSION-LOG.md at the very end. Users had to redo
entire discussion sessions from scratch.
Changes:
- Write DISCUSS-CHECKPOINT.json after each grey area completes,
capturing all decisions, completed/remaining areas, deferred ideas,
and canonical refs
- check_existing step now detects checkpoint files and offers "Resume"
or "Start fresh" — skips already-completed areas on resume
- Checkpoint cleaned up after successful CONTEXT.md write
- Works in both interactive and --auto modes
Closes#1485
Co-Authored-By: Claude Opus 4.6 <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>
Adds `workflow.use_worktrees` config option (default: `true`) that
allows users to disable git worktree isolation for executor agents.
When set to `false`:
- Executor agents run without `isolation="worktree"`
- Plans execute sequentially on the main working tree
- No worktree merge ordering issues or orphaned worktrees
- Normal git hooks run (no --no-verify needed)
This provides an escape hatch for solo developers and users who
experience worktree merge conflicts, as worktree ordering issues
are inherently difficult when parallel agents modify overlapping
files.
Usage:
/gsd:settings → set workflow.use_worktrees to false
Or directly:
gsd-tools config-set workflow.use_worktrees false
Changes:
- config.cjs: add workflow.use_worktrees to valid keys
- planning-config.md: document the option
- execute-phase.md: read config, conditional worktree + sequential mode
- execute-plan.md: conditional worktree in Pattern A
- quick.md: conditional worktree for quick executor
- diagnose-issues.md: conditional worktree for debug agents
- 2 new tests (config set + workflow structural check)
Closes#1451
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Background agents for plan/execute now call Skill(gsd:plan-phase) and
Skill(gsd:execute-phase) instead of reimplementing the workflow steps
inline. This ensures local patches, quality gates, and proper branching
are respected. Also removes --no-verify anti-pattern and specifies
exact Skill names in error handler fallbacks.
Fixes#1453
Adds --only N flag to /gsd:autonomous that restricts execution to a
single phase, enabling safe parallel execution across terminals:
Terminal 1: /gsd:autonomous --only 16
Terminal 2: /gsd:autonomous --only 17
Terminal 3: /gsd:autonomous --only 18
Changes:
- Step 1: Parse --only N alongside --from N (also sets FROM_PHASE)
- Step 2: Filter phase list to exact match when --only active
- Step 4: Skip iteration — single phase does not loop
- Step 5: Skip lifecycle — audit/complete/cleanup only for full runs
- Step 6: Resume message uses --only when active
- Success criteria updated with --only N requirements
Parallel safety: each phase operates in its own .planning/phases/NN-*
directory. ROADMAP.md and STATE.md are read-only during phase execution.
Closes#1383
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The next.md workflow Route 5 referenced `/gsd:complete-phase` which
doesn't exist — only `/gsd:complete-milestone` does. After verify-work
completes for a phase, Route 6 handles advancement to the next phase
automatically, so the dangling reference is simply removed.
Closes#1441
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The CLI (commands.cjs, init.cjs) uses `todos/completed/` but three
workflow files and three FEATURES.md docs referenced `todos/done/`.
This caused completed todos to land in different directories depending
on whether the CLI command or the workflow instructions were followed.
Closes#1438
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-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>
The autonomous workflow ran discuss -> plan -> execute per phase but
skipped ui-phase (design contract) and ui-review (visual audit) for
frontend phases. This adds two conditional steps that match the UI
detection logic already in plan-phase step 5.6:
- Step 3a.5: generates UI-SPEC before planning if frontend indicators
are detected and no UI-SPEC exists
- Step 3d.5: runs advisory UI review after successful execution if a
UI-SPEC is present
Both steps respect workflow.ui_phase and workflow.ui_review config
toggles and skip silently for non-frontend phases.
Fixes#1375
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The repository was transferred from the glittercowboy org to gsd-build,
but several files still referenced the old org in URLs. This updates all
repository URL references across READMEs (all languages), package.json,
and the update workflow. Also removes a duplicate language selector in
the main README header.
Files intentionally unchanged:
- CHANGELOG.md (historical entries)
- CODEOWNERS, FUNDING.yml, SECURITY.md (reference @glittercowboy as a
GitHub username/handle, not a repo URL)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add agent_skills config section that maps agent types to skill directory
paths. At spawn time, workflows load configured skills and inject them
as <agent_skills> blocks in Task() prompts, giving subagents access to
project-specific skill files.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
PR #1139 added <available_agent_types> sections to execute-phase.md and
plan-phase.md to prevent /clear from causing silent fallback to
general-purpose. However, 14 other workflows and 2 commands that also
spawn named GSD agents were missed, leaving them vulnerable to the same
regression after /clear.
Added <available_agent_types> listing to: research-phase, quick,
audit-milestone, diagnose-issues, discuss-phase-assumptions,
execute-plan, map-codebase, new-milestone, new-project, ui-phase,
ui-review, validate-phase, verify-work (workflows) and debug,
research-phase (commands).
Added regression test that enforces every workflow/command spawning
named subagent_type must have a matching <available_agent_types>
section listing all spawned types.
Fixes#1357
Co-Authored-By: Claude Opus 4.6 (1M context) <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>
OpenCode has a `task` tool that supports spawning subagents, but
map-codebase workflow incorrectly listed it under "Runtimes WITHOUT
Task tool". This caused the agent to skip parallel mapping and fall
back to sequential mode, wasting tokens when it self-corrected.
Move OpenCode to the "with Task tool" list and clarify that either
`Task` or `task` (case-insensitive) qualifies. Add regression test.
Fixes#1316
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
`workflow.text_mode: true` (or `--text` flag) now applies to
plan-phase, not just discuss-phase. Fixes#1313.
Changes:
- `init plan-phase` now exposes `text_mode` from config in its JSON output
- plan-phase workflow parses `--text` flag and resolves TEXT_MODE from
init JSON or flag, whichever is set
- All four AskUserQuestion call sites (no-context gate, research prompt,
UI design contract gate, requirements coverage gap) now conditionally
present as plain-text numbered lists when TEXT_MODE is active
- `--text` added to plan-phase command argument-hint and flags docs
- Tests added for init output and workflow references
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
All code-writing agents (gsd-executor, gsd-debugger) were dispatched
without isolation: "worktree", causing branch pollution when agents
switched branches in the shared working tree during concurrent work.
Added isolation="worktree" to all Task() dispatch sites:
- execute-phase.md: executor agent dispatch
- execute-plan.md: Pattern A executor reference
- quick.md: quick task executor dispatch
- diagnose-issues.md: debugger agent dispatch
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- new-project Step 9: suggest /gsd:ui-phase when Phase 1 has UI hint
- progress Route B: show /gsd:ui-phase in options when current phase has UI
- progress Route C: show /gsd:ui-phase in options when next phase has UI
- Detection uses **UI hint**: yes annotation from roadmapper output
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Resolve read-only contradiction: critical_rules now explicitly allows
STATE.md session tracking alongside the forensic report write
2. Add label existence check before gh issue create --label "bug" to
handle repos without a "bug" label gracefully
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Enable multiple Claude Code instances to work on the same codebase
simultaneously by scoping .planning/ state into workstreams.
Core changes:
- planningDir(cwd, ws?) and planningPaths(cwd, ws?) are now workstream-aware
via GSD_WORKSTREAM env var (auto-detected from --ws flag or active-workstream file)
- All bin/lib modules use planningDir(cwd) for scoped paths (STATE.md, ROADMAP.md,
phases/, REQUIREMENTS.md) and planningRoot(cwd) for shared paths (milestones/,
PROJECT.md, config.json, codebase/)
- New workstream.cjs module: create, list, status, complete, set, get, progress
- gsd-tools.cjs: --ws flag parsing with priority chain
(--ws > GSD_WORKSTREAM env > active-workstream file > flat mode)
- Collision detection: transition.md checks for other active workstreams before
suggesting next-milestone continuation (prevents WS A from trampling WS B)
- ${GSD_WS} routing propagation across all 9 workflow files ensures workstream
scope chains automatically through the workflow lifecycle
New files:
- get-shit-done/bin/lib/workstream.cjs (CRUD + collision detection)
- get-shit-done/commands/gsd/workstreams.md (slash command)
- get-shit-done/references/workstream-flag.md (documentation)
- tests/workstream.test.cjs (20 tests covering CRUD, env var routing, --ws flag)
All 1062 tests passing (1042 existing + 20 new workstream tests).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When enabled, /gsd:autonomous chains directly from plan-phase to execute-phase,
skipping smart discuss. A minimal CONTEXT.md is auto-generated from the ROADMAP
phase goal so downstream agents have valid input. Manual /gsd:discuss-phase still
works regardless of the setting.
Changes:
- config.cjs: add workflow.skip_discuss to VALID_CONFIG_KEYS and hardcoded defaults (false)
- autonomous.md: check workflow.skip_discuss before smart_discuss, write minimal CONTEXT.md when skipping
- settings.md: add Skip Discuss toggle to interactive settings UI and global defaults
- config.test.cjs: 6 regression tests for the new config key
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add --pick flag to gsd-tools.cjs for extracting a single field from
JSON output, replacing all jq pipe usage across workflow and reference
files. Since Node.js is already a hard dependency, this eliminates the
need for jq on systems where it is not installed (notably Windows).
Changes:
- gsd-tools.cjs: add --pick <field> global flag with dot-notation and
bracket syntax support (e.g., --pick section, --pick directories[-1])
- Replace 15 jq pipe patterns across 6 workflow/reference files with
--pick flag or inline Node.js one-liner for variable extraction
- Add regression tests for --pick flag behavior
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The gsd-tools.cjs CLI uses hyphenated subcommands (config-get), but
two workflow files used a space-separated form (config get) which
causes "Unknown command: config" errors.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New command that generates a comprehensive project summary from completed
milestone artifacts. Designed for team onboarding — new contributors can
run this against a completed project and understand what was built, how,
and why, with optional interactive Q&A grounded in build artifacts.
- commands/gsd/milestone-summary.md: command definition
- get-shit-done/workflows/milestone-summary.md: 9-step workflow
- tests/milestone-summary.test.cjs: 11 tests (command + workflow validation)
- tests/copilot-install.test.cjs: bump expected skill count 53→54
Reads: ROADMAP, REQUIREMENTS, PROJECT, CONTEXT, SUMMARY, VERIFICATION,
RETROSPECTIVE artifacts. Writes to .planning/reports/MILESTONE_SUMMARY-v{X}.md.
Closes#1298
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The discuss-phase command file contained a 93-line detailed <process>
block that competed with the actual workflow file. The agent treated
this summary as complete instructions and never read the execution_context
files (discuss-phase.md, discuss-phase-assumptions.md, context.md template).
Root cause: Unlike execute-phase and plan-phase commands (which have short
2-line process blocks deferring to the workflow file), discuss-phase had
inline step-by-step instructions detailed enough to act on without reading
the referenced workflow files.
Changes:
- Replace discuss-phase command's <process> block with a short directive
that forces reading the workflow file, matching execute-phase/plan-phase
pattern
- Add MANDATORY instruction that execution_context files ARE the
instructions, not optional reading
- Register workflow.research_before_questions and workflow.discuss_mode
as valid config keys (were missing from VALID_CONFIG_KEYS)
- Fix config key mismatch: workflows referenced "research_questions"
but documented key is "workflow.research_before_questions"
- Move research_before_questions from hooks section to workflow section
in settings workflow
- Add research_before_questions default to config template and builder
- Add suggestion mapping for deprecated hooks.research_questions key
- Add 6 regression tests covering config keys and process block guard
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The installer pathPrefix for global installs replaced os.homedir()
with ~, which does NOT expand inside double-quoted shell commands
in POSIX shells. This caused MODULE_NOT_FOUND errors when executing
commands like: node "~/.claude/get-shit-done/bin/gsd-tools.cjs"
Changed pathPrefix to use $HOME instead of ~, which correctly expands
inside double quotes. Also fixed a quoted-tilde instance in do.md.
- bin/install.js: $HOME prefix instead of ~ for global installs
- get-shit-done/workflows/do.md: node "$HOME/..." instead of "~/"
- tests/path-replacement.test.cjs: updated + 3 new regression tests
Closes#1284
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
