Sequential execution is now the recommended default. Parallel
execution is still being refined and may not yield best results.
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>
Simple command to check background agent status:
- Shows running/completed agents from agent-history.json
- Uses TaskOutput to poll agent status
- --wait flag blocks until all complete
- Reports time savings vs sequential execution
Inspired by PR #43 but intentionally minimal (117 lines vs 317).
Skipped task-level parallelization display (not implementing that).
Moves config.json creation to its own step so the parallelization
question isn't skipped. Matches pattern used by mode and depth steps.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 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>
- Create plan-fix command to generate FIX.md from ISSUES.md
- Add Route E to progress.md for detecting unaddressed UAT issues
- Add verify-work and plan-fix to README commands table
- Credit OracleGreyBeard for verify-work contribution
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove future phases from roadmap and renumber subsequent phases.
- Validates phase is unstarted (no SUMMARY.md files)
- Deletes phase directory
- Renumbers all subsequent phases (integers and decimals)
- Updates ROADMAP.md and STATE.md
- Git commit preserves historical record
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 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 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>
Reads STATE.md, determines next action, executes via SlashCommand.
All checkpoints auto-approved in yolo mode. No human intervention.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
TDD context was only loaded indirectly through workflows.
Now explicitly loaded in plan-phase and execute-plan commands.
🤖 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>
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>
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>
- new-project.md detects existing code, offers /gsd:map-codebase first
- plan-phase loads relevant codebase context based on phase type
- execute-phase updates codebase map incrementally after execution
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- commands/gsd/map-codebase.md: slash command entry point
- get-shit-done/workflows/map-codebase.md: workflow with 6 process steps
- Documents 4 parallel Explore agents and 7 output files
- Agent orchestration to be implemented in plan 02-02
- Add continuation-format.md reference defining the standard format
- Replace "## To Continue" with "## ▶ Next Up"
- Show plan/phase name + description instead of just command paths
- Add `/clear` explanation: "fresh context window"
- Change "Other options" to "Also available"
- Add /gsd:research-phase to phase planning options
- Add visual separators and completion headers
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Claude has no context before the user describes their idea.
Can't generate useful options from nothing.
Flow: freeform "what do you want to build?" → THEN AskUserQuestion
for intelligent follow-ups based on what they said.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Shell commands in <context> sections using !` backticks trigger
permission checks for users not in dangerously-skip-permissions mode.
Replaced with @-file references where needed; process logic handles
missing files via allowed tools (Read, Glob, Grep).
Affected commands: new-project, progress, create-roadmap,
research-project, pause-work, consider-issues
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
End-of-command workflows now show explicit instructions to run /clear
and paste the next command, rather than offering numbered options that
invoke SlashCommand directly. This prevents users from accidentally
exhausting context by continuing work in the same session.
- Updated 16 files (commands and workflows)
- YOLO mode auto-continues preserved (user explicitly chose automation)
- In-workflow decisions like consider-issues preserved
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove silent="true" which caused step to be skipped
- Make setup step explicit with MANDATORY instruction
- Check for both .git directory AND .git file (worktrees/submodules)
- Add explicit "You MUST run using Bash tool" instruction
Prevents commits going to parent repo when initializing
projects in subdirectories.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
All questioning workflows now require AskUserQuestion tool for every
question, not just decision gates. Inline text questions are prohibited.
Updated: questioning.md, new-project.md, discuss-phase.md,
discuss-milestone.md, and their workflow files.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update user-facing descriptions to reflect vision-focused workflow:
- discuss-phase: captures vision, not constraints/risks
- list-phase-assumptions: see Claude's plan, course-correct vision
- discuss-milestone: features first, not scope/constraints
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Show slash commands inline so users can copy them to fresh context,
matching pattern used by other GSD commands.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Decision gate now explicitly uses AskUserQuestion tool, enabling
the loop behavior where users can keep exploring before finalizing.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Research is now optimized for Claude Code implementation quality:
- PROJECT.md-driven (features, constraints, questions, decisions)
- High-confidence only (no low-quality padding)
- 3 focused files: stack.md, implementation.md, risks.md
- Code examples with current vs deprecated patterns
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace interrogation-style domain checklist with conversation arc
- Focus on following user's thread, not walking a checklist
- Add good vs bad examples to guide natural questioning
- Update new-project to use new philosophy
Questioning now helps users discover and articulate their vision
through collaborative thinking instead of form-filling.
- Create /gsd:create-roadmap slash command entry point
- Add check_research step to workflow after check_brief
- Incorporate research findings into phase structure planning
- Add Research Context section to roadmap output when research exists
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
