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>
Context isolation is the primary goal, not parallelization.
Even sequential plans spawn separate subagents for fresh 200k context.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add parallel-aware plan example with vertical slice pattern
- Add sequential plan example with explicit dependencies
- Document key differences between parallel and sequential plans
- Update categorization table to show frontmatter-aware criteria
- Add categorization priority documentation
- Update calculate_wave() to check frontmatter depends_on first
- Handle parallelizable: false as implicit Wave 2+ assignment
- Fall back to inferred requires only when no frontmatter
- Add [frontmatter] annotation in wave output for plans using new fields
- Add PLAN_PARALLELIZABLE, PLAN_DEPENDS_ON, PLAN_FILES_EXCLUSIVE arrays
- Check for parallelizable, depends_on, files_exclusive in plan frontmatter
- Use frontmatter values directly when present
- Fall back to inference logic for old plans without frontmatter
- Document dependency detection priority
- 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
- parallelizable: marks plan as safe for concurrent execution
- depends_on: explicit plan dependencies
- files_exclusive: conflict detection for parallel agents
- Added frontmatter_guidance section with usage rules
- Updated good_examples with parallel/sequential examples
- Sequential execution example with all fields
- Plan-level parallel execution example
- Queued with dependency example
- Document parallel_group format conventions
- Command now loads both workflows (execution + orchestration)
- Agents commit tasks normally (removed DON'T COMMIT instruction)
- Orchestrator only commits metadata after all agents complete
- No duplication - single source of truth for execution logic
Adds /gsd:add-todo and /gsd:check-todos commands for capturing
ideas during work sessions without losing context.
Features:
- Capture todos from conversation context or explicit description
- Structured frontmatter (created, title, area, files)
- Area inference from file paths for grouping
- Duplicate detection before creating
- Filter todos by area
- Route to appropriate action (work now, add to phase, brainstorm)
- Git commits on capture and when starting work
Closes#48
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Decimal phases now use printf "%02d" formatting to match integer phases.
Before: 6.1-01-PLAN.md vs 06-04-PLAN.md (inconsistent)
After: 06.1-01-PLAN.md vs 06-04-PLAN.md (consistent)
Closes#51
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add ability to resume interrupted subagent executions using Task tool's
resume parameter. Tracks agent IDs during execution and enables seamless
continuation after session timeout, rate limits, or crashes.
- New /gsd:resume-task command for resuming interrupted agents
- Agent ID tracking in execute-phase workflow
- Dual storage: current-agent-id.txt (fast) + agent-history.json (audit)
- Auto-detection of interrupted agents in resume-project workflow
- File conflict warnings before resume
Closes#37
Co-Authored-By: davesienkowski <davesienkowski@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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>
Add /gsd:verify-work to "Also available" sections in execute-phase workflow:
- Route A: After plan completion, before next plan
- Route B: After phase completion, before next phase
- Route C: After milestone completion, before archiving
Users can now easily run manual acceptance testing at any completion point.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Phase-scoped issues format ({phase}-{plan}-ISSUES.md)
- Separate from global ISSUES.md (enhancements)
- Severity guide and numbering conventions
- Workflow for resolution tracking
- GSD-compliant XML structure with terse step names
- All user interaction via AskUserQuestion
- Issues logged to phase-scoped file (not global ISSUES.md)
- References uat-issues.md template
- Rewrite offer_next step in execute-phase.md as mandatory verification gate
- Rewrite offer_next_phase step in transition.md with explicit verification
- Rewrite route step in progress.md with numbered verification steps
- Replace broken regex [0-9] (only matched single digits) with ROADMAP.md reading
- Add decision tables mapping conditions to explicit routes (A, B, C, D)
- Require Claude to "State the counts" before any routing decision
- Add "Do NOT skip this verification" instruction to prevent premature completion claims
Fixes issue where Claude would declare "phase complete" or "milestone complete"
without verifying remaining plans actually exist.
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
- Add MILESTONE-CONTEXT.md template for handoff between commands
- discuss-milestone now writes context to .planning/MILESTONE-CONTEXT.md
- create-milestone reads context file and deletes after use
Fixes#11🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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>
- Each task commits immediately after completion (feat/fix/test/refactor)
- Plan completion commits metadata only (docs: SUMMARY + STATE + ROADMAP)
- Git history becomes primary context source for future Claude sessions
- Better bisect granularity, failure recovery, and revert capabilities
Changes:
- execute-phase.md: Added <task_commit> protocol and per-task commit flow
- execute-plan.md: Updated commit rules and success criteria
- git-integration.md: New task-completion format, strategy rationale
- tdd.md: Aligned TDD commits with standard task commit pattern
- summary.md: Added Task Commits section with commit hashes
- README.md: Rewrote git history section with atomic commit benefits
- scope-estimation.md: Clarified commit counts per plan
- principles.md: Added <atomic_commits> section explaining strategy
Each plan now produces 3-4 commits (2-3 task commits + 1 metadata commit)
instead of single monolithic commit. Optimizes observability for solo
developer + Claude Code workflow.
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>
- Consolidated checkpoints.md with automation reference (287 lines from 1,121)
- Compressed plan-format.md to reference card (127 lines from 397)
- Deleted cli-automation.md (merged into checkpoints.md)
- Updated plan-phase.md to remove stale reference
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds bash logic to count PLAN vs SUMMARY files before deciding
whether to offer next plan or next phase. Fixes bug where GSD
would skip remaining plans in a phase.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
PROJECT.md evolves throughout project lifecycle:
- Requirements have states: Validated, Active, Out of Scope
- Decisions track outcomes: Good, Revisit, Pending
- Phase transitions update requirements and log decisions
- Milestone completions trigger full PROJECT.md review
STATE.md now references PROJECT.md (not a copy):
- Claude reads PROJECT.md directly for full context
- Smaller STATE.md footprint (~100 lines)
- Project Reference section with core value and focus
Brownfield projects infer Validated requirements from existing code.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Agent prompts now explicitly require file paths in findings
- Templates updated with backtick-formatted path examples
- CONCERNS.md examples show Files: field for every issue
- ARCHITECTURE.md now welcomes file paths as concrete examples
- Makes codebase docs actionable for Claude during planning
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The limit was causing loss of useful context, especially code examples
in TESTING.md and CONVENTIONS.md. Document quality > arbitrary brevity.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
