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>
Adds automated feedback architecture research to gsd-phase-researcher,
enforces it as Dimension 8 in gsd-plan-checker, and introduces
{phase}-VALIDATION.md as the per-phase validation contract.
Ensures every phase plan includes automated verify commands before
execution begins. Opt-out via workflow.nyquist_validation: false.
Closes#122 (partial), related #117
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>
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>
Closes#253 — plans were silently created without CONTEXT.md, and
discuss-phase didn't warn when plans already existed.
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>
When init commands include many file contents (state, roadmap, requirements,
etc.), the JSON output can exceed Claude Code's Bash tool buffer (~50KB),
causing parse errors. The output() function now auto-detects large payloads
and writes to a tmpfile, returning @file:/path instead. All workflows that
consume init output handle both formats.
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>
Add opt-in mechanism to chain discuss → plan → execute automatically
via Task() subagents, eliminating manual /clear + paste overhead.
- Add `--auto` flag to discuss-phase and plan-phase commands
- Add `workflow.auto_advance` config toggle (default: false)
- Add auto_advance step to discuss-phase workflow (spawns plan-phase)
- Add step 14 to plan-phase workflow (spawns execute-phase)
- Add auto_advance toggle to /gsd:settings
Chain stops gracefully on INCONCLUSIVE, CHECKPOINT, or verification
failures. No work lost — artifacts persist at each step.
Closes#541
Co-Authored-By: Claude Opus 4.5 <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>
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>
Commands load agent expertise directly via Task tool spawning.
Thin orchestrator pattern — agents have methodology baked in.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replaced 868-line workflow with deprecation notice
- Points to agents/gsd-planner.md for methodology
- Documents historical content for reference
- Kept file for git history
Unify gap handling - whether discovered by code verification or user
testing, gaps feed into the same plan-phase --gaps workflow.
Changes:
- Delete commands/gsd/plan-fix.md (redundant)
- Update verify-work to route to plan-phase --gaps
- Update progress Route E to detect UAT gaps
- Change UAT.md "Issues" section to "Gaps" with YAML format
- Extend plan-phase --gaps to read from both VERIFICATION.md and UAT.md
- Update diagnose-issues to output gaps in YAML format
- Update all references (debug, templates, workflows)
One path: gap discovered → diagnosed → plan-phase --gaps → fixed
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The ~/.claude/skills/expertise/ system was personal tooling
that doesn't exist for other users. Removed from:
- create-roadmap workflow (detect_domain step)
- plan-phase workflow (domain loading)
- roadmap template (Domain Expertise section)
- phase-prompt template (domain frontmatter)
- plan-format reference (domain field)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add verify_phase_goal step to execute-phase workflow
- Verifier outputs structured gaps: YAML for planner consumption
- Add --gaps flag to plan-phase for gap closure mode
- Route by verification status: passed, gaps_found, human_needed
- Gap closure creates sequential plans (04, 05...) from verification gaps
- User stays in control at each decision point
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove the global ISSUES.md deferred enhancement tracking system.
- Delete /gsd:consider-issues command (never used)
- Delete issues.md template (never instantiated)
- Remove Rule 5 from deviation rules (never triggered)
- Remove all ISSUES.md, ISS-XXX, and "deferred issues" references
- Update STATE.md to track pending todos instead
The ISSUES.md system was designed to capture non-critical enhancements
during plan execution via "Rule 5", but it never fired in practice
across 100+ projects. The system added ~350 lines of dead code.
The /gsd:add-todo and /gsd:check-todos system serves the same purpose
and is actually used.
Note: UAT *-ISSUES.md files (per-plan, created by /gsd:verify-work)
are unaffected - those are a separate, active system.
Closes#56
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Wave numbers now computed during plan-phase and stored in PLAN.md
frontmatter. Execute-phase reads wave directly instead of deriving
from depends_on at runtime.
- Add assign_waves step to plan-phase workflow
- Add wave field to frontmatter (plan-format, phase-prompt template)
- Simplify execute-phase: remove analyze_dependencies and group_into_waves
- Replace with group_by_wave that just reads frontmatter integers
Co-Authored-By: Claude <noreply@anthropic.com>
Restored context-budget reasoning for why TDD features get dedicated plans:
- TDD requires 2-3 execution cycles consuming 50-60% context
- Test framework setup handled in first TDD plan's RED phase
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove confusing `parallelizable` boolean field. It was redundant -
execute-phase already computes parallelizability from `depends_on`
and file conflicts.
Changes:
- Remove `parallelizable: true|false` from plan frontmatter
- Rename `files_exclusive` to `files_modified` (clearer intent)
- Simplify execute-phase dependency detection logic
- Update phase-prompt template and plan-phase workflow
Parallelization is now fully automatic based on:
- `depends_on: []` (empty = independent)
- `files_modified: [...]` (no overlap = can parallelize)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Routes to batch execution when 2+ plans exist, with execute-plan
as alternative for interactive mode.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Include parallelizable, depends_on, files_exclusive in frontmatter
- Rules for parallelizable field determination
- Parallel-aware context section guidance
- Avoid reflexive SUMMARY references when parallel
- File ownership analysis per task group
- Detect unnecessary inter-plan dependencies
- Restructure for vertical slices when beneficial
- Mark plans with parallelization frontmatter values
- Reads .planning/config.json parallelization settings early
- Documents planning behavior when parallel enabled vs disabled
- Placed after load_project_state, before load_codebase_context
- Default: assume parallelization enabled for new projects
Front-load mindset guidance before process steps:
- Secure by design: assume hostile input
- Performance by design: assume production load
- Observable by design: plan for self-debugging
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Each phase workflow now commits its artifacts immediately:
- discuss-phase.md commits CONTEXT.md
- research-phase.md commits RESEARCH.md
- plan-phase.md commits PLAN.md (and DISCOVERY.md)
- execute-phase.md commits only execution artifacts (SUMMARY, STATE, ROADMAP)
Planning artifacts are inputs to execution and should be saved when created.
Execution artifacts are outputs and are committed after execution completes.
Closes#12
TDD requires 2-3 execution cycles (RED → GREEN → REFACTOR), each with
file reads, test runs, and potential debugging. This consumes 40-50%
of context for a single feature. Dedicated TDD plans ensure full
quality throughout the cycle.
- TDD plans use `type: tdd` frontmatter with `<feature>` element
- One feature per TDD plan (batching defeats the purpose)
- Target ~40% context usage for TDD plans
- Standard plans handle non-TDD work with 2-3 tasks
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Depth sets a ceiling on compression, not a floor on expansion.
Small phases stay small even in comprehensive mode.
- Comprehensive auth = 8 plans (work warrants it)
- Comprehensive "add favicon" = 1 plan (that's all it is)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds depth setting (quick/standard/comprehensive) to control how many
phases and plans get created. Tasks per plan stays constant at 2-3.
- Quick: 3-5 phases, 1-3 plans each
- Standard: 5-8 phases, 3-5 plans each
- Comprehensive: 8-12 phases, 5-10 plans each
Depth increases plan COUNT, never plan SIZE. More plans = more
thoroughness with same quality per plan.
Files changed:
- new-project.md: depth question after mode
- config.json: depth field added
- create-roadmap.md: depth-aware phase guidance
- plan-phase.md: depth-aware plan splitting
- scope-estimation.md: depth calibration section
- create-milestone.md: removed hardcoded 3-6 limit
- new-milestone.md: removed hardcoded 3-6 limit
- roadmap.md template: depth-aware guidance
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add references/tdd.md with detection heuristics, red-green-refactor cycle
- Add tdd_annotation section to plan-format.md with task structure
- Expand plan-phase.md with TDD detection and annotation guidance
- Add tdd_execution section to execute-phase.md with commit patterns
- TDD-aware task routing in execute step
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove decision_gate step (redundant after confirm_breakdown approval)
- Restore explicit bash commands in load_codebase_context, identify_phase,
read_project_history, and gather_phase_context for consistent behavior
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
