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>
The <evolution> block in templates/project.md defined requirement lifecycle
rules (validate, invalidate, add, log decisions) but these instructions
only existed in the template — they never made it into the generated
PROJECT.md that agents actually read during phase transitions.
Changes:
- new-project.md: Add ## Evolution section to generated PROJECT.md with
the phase transition and milestone review checklists
- new-milestone.md: Ensure ## Evolution section exists in PROJECT.md
(backfills for projects created before this feature)
- execute-phase.md: Add .planning/PROJECT.md to executor <files_to_read>
so executors have project context (core value, requirements, evolution)
- templates/project.md: Add comment noting the <evolution> block is
implemented by transition.md and complete-milestone.md
- docs/ARCHITECTURE.md, docs/FEATURES.md: Note evolution rules in
PROJECT.md descriptions
- CHANGELOG.md: Document the new Evolution section and executor context
Fixes#1039
All 755 tests pass.
Add regression_gate step between executor completion and verification
in execute-phase workflow. Runs prior phases' test suites to catch
cross-phase regressions before they compound.
- Discovers prior VERIFICATION.md files and extracts test file paths
- Detects project test runner (jest/vitest/cargo/pytest)
- Reports pass/fail with options to fix, continue, or abort
- Skips silently for first phase or when no prior tests exist
Changes:
- execute-phase.md: New regression_gate step
- CHANGELOG.md: Document regression gate feature
- docs/FEATURES.md: Add REQ-EXEC-09
Fixes#945
Co-authored-by: TÂCHES <afromanguy@me.com>
The agent was telling users to run '/gsd:transition' after phase completion,
but this command does not exist. transition.md is an internal workflow invoked
by execute-phase during auto-advance.
Changes:
- Add <internal_workflow> banner to transition.md declaring it is NOT a user command
- Add explicit warning in execute-phase completion section that /gsd:transition
does not exist
- Add 'only suggest commands listed above' guard to prevent hallucination
- Update resume-project.md to avoid ambiguous 'Transition' label
- Replace 'ready for transition' with 'ready for next step' in execute-plan.md
Fixes#1081
Two gaps in the standard workflow cycle caused planning document drift:
1. PROJECT.md was never updated during discuss → plan → execute → verify.
Only transition.md (optional) and complete-milestone evolved it.
Added an 'update_project_md' step to execute-phase.md that evolves
PROJECT.md after phase completion: moves requirements to Validated,
updates Current State, bumps Last Updated timestamp.
2. cmdPhaseComplete() in phase.cjs advanced 'Current Phase' but never
incremented 'Completed Phases' counter or recalculated 'percent'.
Added counter increment and percentage recalculation based on
completed/total phases ratio.
Addresses the workflow-level gaps identified in #956:
- PROJECT.md evolution in execute-phase (gap #2)
- completed_phases counter not incremented (gap #1 table row 3)
- percent never recalculated (gap #1 table row 4)
Fixes#956
Copilot's subagent spawning (Task API) may not properly return completion
signals to the orchestrator, causing it to hang indefinitely waiting for
agents that have already finished their work.
Added <runtime_compatibility> section to execute-phase.md with:
- Runtime-specific subagent spawning guidance (Claude Code, Copilot, others)
- Fallback rule: if agent completes work but orchestrator doesn't get the
signal, treat as success based on spot-checks (SUMMARY.md exists, commits
present)
- Sequential inline execution fallback for runtimes without reliable Task API
Fixes#1128
Adds --interactive flag to /gsd:execute-phase that changes execution from
autonomous subagent delegation to sequential inline execution with user
checkpoints between tasks.
Interactive mode:
- Executes plans sequentially inline (no subagent spawning)
- Presents each plan to user: Execute, Review first, Skip, Stop
- Pauses after each task for user intervention
- Dramatically lower token usage (no subagent overhead)
- Maintains full GSD planning/tracking structure
Changes:
- execute-phase.md: new check_interactive_mode step with full interactive flow
- execute-phase command: documented --interactive flag in argument-hint and context
Use cases:
- Small phases (1-3 plans, no complex dependencies)
- Bug fixes and verification gap closure
- Learning GSD workflow
- When user wants to pair-program with Claude under GSD structure
Fixes#963
GSD executor agents ignore MCP tools (e.g. jCodeMunch) even when CLAUDE.md
explicitly instructs their use. Agents default to Grep/Glob because those
are explicitly referenced in workflow patterns.
Added MCP tool instructions to:
- execute-phase.md: <mcp_tools> section in executor agent prompt telling
agents to prefer MCP tools over Grep/Glob when available
- execute-plan.md: Step 2 in execute section with MCP tool fallback guidance
Agents now:
1. Check if CLAUDE.md references MCP tools
2. Prefer MCP tools for code navigation when accessible
3. Fall back to Grep/Glob if MCP tools are not available
Fixes#973
After /clear, Claude Code sometimes loses awareness of custom agent types
and falls back to 'general-purpose'. This happens because the model doesn't
re-read .claude/agents/ after context reset.
Added <available_agent_types> sections to:
- execute-phase.md: lists all 12 valid GSD agent types with descriptions
- plan-phase.md: lists the 3 agent types used during planning
The explicit listing in workflow instructions ensures the model always has
an unambiguous reference to valid agent types, regardless of whether
.claude/agents/ was re-read after /clear.
Fixes#949
The offer_next step in execute-phase.md suggests /gsd:transition to users
when auto-advance is disabled. This command does not exist as a registered
skill — transition.md is an internal workflow only invoked inline during
auto-advance chains (line 456).
Replace with /gsd:discuss-phase and /gsd:plan-phase which are the actual
user-facing equivalents for transitioning between phases.
No impact on auto-advance path — that invokes transition.md by file path,
not as a slash command.
Co-authored-by: Piyush Rane <piyush.rane@inmobi.com>
- fix(frontmatter): handle CRLF line endings in extractFrontmatter,
spliceFrontmatter, and parseMustHavesBlock — fixes wave parsing on
Windows where all plans reported as wave 1 (#1085)
- fix(hooks): remove duplicate const cwd declaration in
gsd-context-monitor.js that caused SyntaxError on every PostToolUse
invocation (#1091, #1092, #1094)
- feat(state): add 'state begin-phase' command that updates STATUS,
Last Activity, Current focus, Current Position, and plan counts
when a new phase starts executing (#1102, #1103, #1104)
- docs(workflow): add state begin-phase call to execute-phase workflow
validate_phase step so STATE.md is current from the start
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.
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>
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>
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>
* 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 `--auto` flag on discuss-phase and plan-phase chains stages automatically:
discuss → plan → execute, each in a fresh context window. Currently the chain
is broken because auto-advance spawns `Task(prompt="Run /gsd:plan-phase --auto")`
which requires the Skill tool — but Skills don't resolve inside Task subagents.
Result: plan-phase never runs from discuss's auto-advance, execute-phase never
runs from plan's auto-advance, and gsd-executor subagents are never spawned.
Fix: Replace `Task(prompt="Run /gsd:XXX")` with Task calls that tell the
subagent to read the workflow .md file directly via @file references — the same
pattern that already works for gsd-executor spawning in execute-phase.
Changes:
- execute-phase.md: Add --no-transition flag handling so execute-phase can
return status to parent instead of running transition.md when spawned by
plan-phase's auto-advance
- plan-phase.md: Replace Skill-based Task call with direct @file reference
to execute-phase.md, passing --no-transition to prevent transition chaining
- discuss-phase.md: Replace Skill-based Task call with direct @file reference
to plan-phase.md, with richer return status handling (PHASE COMPLETE,
PLANNING COMPLETE, PLANNING INCONCLUSIVE, GAPS FOUND)
Nesting depth: discuss → Task(plan) → Task(execute) → Task(executor) = 3 levels
max. Each level gets clean 200k context.
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>
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>
Wire execute-phase to invoke transition.md inline when --auto flag or
workflow.auto_advance config is set, propagate --auto through transition
to next phase invocations, add config-get command to gsd-tools, and fix
broken "config get" calls to use hyphenated "config-get" subcommand.
Closes#344
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add optional phase archival to milestone completion and a standalone
/gsd:cleanup command for retroactive use. Phase dirs move to
.planning/milestones/v{X.Y}-phases/, reducing phases/ clutter after
multiple milestones.
Core changes:
- getArchivedPhaseDirs() and searchPhaseInDir() helpers in gsd-tools
- findPhaseInternal() searches archives when phase not found in current
- cmdPhasesList() accepts --include-archived flag
- cmdHistoryDigest() scans both current and archived phases
- cmdMilestoneComplete() accepts --archive-phases flag
- Workflow globs replaced with find-phase/phases-list CLI calls
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>
Three routing fixes:
- transition.md checks for CONTEXT.md before routing — discuss-phase when
missing, plan-phase when present (matches progress.md behavior)
- execute-phase.md offer_next delegates to transition.md instead of emitting
duplicate "Next Up" blocks
- discuss-phase.md adds explicit handling for "Other" free-text responses
Closes#530
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace NL instructions in execute-plan and execute-phase workflows with
deterministic `roadmap update-plan-progress` command that counts PLAN vs
SUMMARY files on disk. Prevents LLM from miscounting plan progress.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add `close_parent_artifacts` step to execute-phase workflow that resolves
parent UAT gaps and debug sessions when a decimal/polish phase completes.
Co-Authored-By: Claude Opus 4.6 <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>
Claude Code v2.1.27+ has a bug where all Task tool agents report
"failed" due to `classifyHandoffIfNeeded is not defined` — a function
called but never defined in the cli.js bundle. The error fires AFTER
all agent work completes, so actual work is always done.
This adds spot-check fallback logic to execute-phase, execute-plan,
and quick workflows: when an agent reports this specific failure,
verify artifacts on disk (SUMMARY.md exists, git commits present).
If spot-checks pass, treat as successful.
Tracked upstream: anthropics/claude-code#24181
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The workflow showed the prompt content but didn't wrap it in Task()
with the required subagent_type parameter. This caused the orchestrator
to spawn generic task agents instead of the specialized gsd-executor.
Now shows the full Task() call with subagent_type and model parameters.
Fixes#455
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(execute-phase): pass file paths to subagents instead of content
The --include flag added in fa81821 caused orchestrator context bloat
by reading STATE, config, and plan files into the orchestrator's context,
then embedding all content in Task() prompts.
With multiple plans, this consumed 50-60%+ of context before execution.
Fix: Pass file paths only. Subagents read files themselves in their
fresh 200k context. Orchestrator stays lean (~10-15% as intended).
Fixes#479
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: respect commit_docs=false in execute-plan and debugger workflows
Two code paths bypassed the commit_docs configuration check, causing
.planning files to be intermittently committed when commit_docs=false:
1. execute-plan.md: update_codebase_map step ran `git add .planning/codebase/*.md`
unconditionally — now gated behind commit_docs check
2. gsd-debugger.md: used `git add -A` which stages .planning/ files — replaced
with explicit individual file staging and proper commit_docs conditional
Fixes#478https://claude.ai/code/session_013yS1F2VR3Jn2pdwqr5NuDo
* fix: route all .planning commits through gsd-tools.js CLI
Instead of wrapping direct git commands in markdown conditionals,
both bypass paths now use gsd-tools.js commit which has the
commit_docs check built in:
1. execute-plan.md: uses `gsd-tools.js commit --amend` for codebase
map updates (new --amend flag added to CLI)
2. gsd-debugger.md: code commit uses direct git (no .planning files),
planning docs commit uses gsd-tools.js commit
Also added --amend support to gsd-tools.js commit command so the
execute-plan codebase map step can amend the previous metadata commit.
Fixes#478https://claude.ai/code/session_013yS1F2VR3Jn2pdwqr5NuDo
* docs: update reference docs to use gsd-tools.js CLI for all .planning commits
Reference documentation showed direct git add/commit patterns for
.planning files, which agents copy-paste and bypass the commit_docs
check. Updated all three reference files to show gsd-tools.js commit
as the canonical pattern:
- git-planning-commit.md: replaced manual bash conditionals with CLI
- git-integration.md: replaced direct git add/commit in initialization,
plan-completion, and handoff examples
- planning-config.md: replaced conditional git example with CLI call
https://claude.ai/code/session_013yS1F2VR3Jn2pdwqr5NuDo
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Workflows were calling init commands to get parsed JSON metadata, then
immediately reading the same files again with cat to pass raw content
to agents. This wastes context tokens.
Changes:
- Add --include flag to init execute-phase, plan-phase, and progress
- Support includes: state, config, roadmap, requirements, context,
research, verification, uat, project
- Update plan-phase.md to use --include (removes 6 cat calls)
- Update execute-phase.md to use --include (removes 2 cat calls)
- Update execute-plan.md to use --include (removes 2 cat calls)
- Update progress.md to use --include (removes 4 cat calls)
- Add 7 tests for --include functionality
Token savings: ~5,000-10,000 tokens per plan-phase execution,
~1,500-3,000 per other workflow executions.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add three new commands that extract structured data from GSD files,
reducing context usage by returning only parsed fields instead of
raw file content:
- phase-plan-index: Plans grouped by wave with metadata (id, wave,
autonomous, objective, files_modified, task_count, has_summary)
- state-snapshot: Parsed STATE.md fields (current phase, decisions,
blockers, session info)
- summary-extract: Frontmatter extraction with optional --fields filter
Update workflows to use new commands:
- execute-phase: Use phase-plan-index instead of ls + grep loop
- plan-phase: Use state-snapshot for decisions
- research-phase: Use state-snapshot for decisions
- complete-milestone: Use summary-extract for one-liners
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Reverts af7a057 "feat: add GSD Memory cross-project knowledge system"
The memory system needs more work before shipping:
- Workflow integration is incomplete (writes but doesn't query)
- UX requires too much manual intervention
- Setup friction exceeds value for most users
Preserved on branch `memory-wip` for continued development.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
