Runs research → requirements → roadmap automatically after config
questions. Requires idea document via @ reference. Auto-includes all
table stakes features plus features mentioned in provided document.
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>
Implements MCP server for semantic search across GSD projects:
MCP Tools:
- gsd_memory_search: Search across all registered projects
- gsd_memory_decisions: Find decisions from SUMMARY/PROJECT.md
- gsd_memory_patterns: Find patterns from SUMMARY.md
- gsd_memory_pitfalls: Find pitfalls from RESEARCH.md
- gsd_memory_stack: Find tech stack entries
- gsd_memory_register: Register project with memory
- gsd_memory_index: Trigger indexing/update
- gsd_memory_status: Show system status
Architecture:
- QMD wrapper with grep fallback when QMD unavailable
- YAML frontmatter extractors for GSD document types
- Project registry at ~/.gsd/projects.json
- Auto-install via bin/install.js for Claude Code
Workflow integrations:
- new-project: Registers project with memory
- plan-phase: Indexes after planning
- execute-phase: Indexes after execution
- complete-milestone: Indexes milestone completion
- Researcher agents query memory before Context7
Tests: 117 passing (66 unit + 51 integration)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Custom subagents cannot access MCP tools due to Claude Code bug #13898.
This affects gsd-phase-researcher, gsd-project-researcher, and gsd-planner
which need Context7 for documentation lookups.
Fix: Switch to general-purpose agent (which has MCP access) and have it
read the agent instruction file as its first action. The specialized
behavior comes from the prompt, not the agent definition.
Closes#161
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Rolled back the intel system due to overengineering concerns:
- 1200+ line hook with SQLite graph database
- 21MB sql.js dependency
- Entity generation spawning additional Claude calls
- Complex system with unclear value
Removed:
- /gsd:analyze-codebase command
- /gsd:query-intel command
- gsd-intel-index.js, gsd-intel-session.js, gsd-intel-prune.js hooks
- gsd-entity-generator, gsd-indexer agents
- entity.md template
- sql.js dependency
Preserved:
- Model profiles feature
- Statusline hook
- All other v1.9.x improvements
-3,065 lines removed
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add model_profile question (balanced/quality/budget) to Round 2
- Add model_profile to config.json schema
- Reword agent questions to be clearer:
- "Spawn Plan Researcher?" → "Research before planning each phase?"
- "Spawn Plan Checker?" → "Verify plans will achieve their goals?"
- "Spawn Execution Verifier?" → "Verify work satisfies requirements after each phase?"
- Update descriptions to explain value, not mechanics
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds switchable model profiles (quality/balanced/budget) to control
which Claude model each agent uses, balancing quality vs token spend.
New files:
- get-shit-done/references/model-profiles.md - profile lookup table
- commands/gsd/set-profile.md - runtime profile switching
Updated orchestrators to resolve model before spawning agents:
- new-project, new-milestone (7 calls each)
- plan-phase (4 calls)
- execute-phase (3 calls)
- audit-milestone, debug, research-phase, quick (1-2 calls each)
- workflows: execute-phase, execute-plan, verify-work, map-codebase
Profile stored in .planning/config.json as model_profile.
Default: "balanced" (Opus for planning, Sonnet for execution).
Closes#160
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- SessionStart now reads pre-generated summary.md directly
- No more JSON parsing of potentially large index.json
- Added guidance: .planning/intel/ should always be gitignored
(changes constantly, can be regenerated with /gsd:analyze-codebase)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create .planning/intel/ during Phase 1 setup
- Document intel directory in Creates and Output sections
- Directory prepared for PostToolUse hook population
- Split Phase 5 into two rounds of questions
- Round 1: core settings (mode, depth, parallel, git tracking)
- Round 2: workflow agents (researcher, plan checker, verifier)
- Add explainer table before workflow questions
- Include workflow section in config.json schema
- Note that /gsd:settings can update later
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds 4th question to initial config asking whether to commit planning
docs to git. When user selects "No", sets planning.commit_docs: false
and adds .planning/ to .gitignore.
Builds on #107 (uncommitted planning mode) by surfacing the option
during project initialization.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase directories are now created on-demand when discuss-phase or
plan-phase first touches a phase, rather than upfront by roadmapper.
Prevents duplicate folders when roadmapper names phases differently
than what discuss/plan-phase derives from the roadmap.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updated routing in:
- new-project.md
- create-roadmap.md (command and workflow)
- progress.md (routes B and C)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Researchers are always spawned in parallel (4 at once). Committing is
now exclusively handled by the orchestrator or synthesizer agent after
all researchers complete.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add ui-brand.md reference with visual patterns:
- Stage banners with GSD ► prefix
- Checkpoint boxes (62-char width)
- Status symbols vocabulary
- Next Up routing blocks
Update orchestrators to use branded output.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Present proposed roadmap nicely inline (table + phase details)
- Use AskUserQuestion to confirm before committing
- Options: Approve, Adjust phases, Review full file
- Loop on adjustments until user approves
Previously, roadmap was committed immediately without user review.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create dedicated synthesizer agent to handle research synthesis
- Move SUMMARY.md creation from main orchestrator to subagent
- Reduces main context usage (~2000+ lines of research output)
- Synthesizer reads 4 research files and produces unified summary
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Consolidates 4 separate commands into one unified flow:
- /gsd:new-project now handles: questioning → research → requirements → roadmap
- Creates gsd-roadmapper agent for heavy lifting (goal-backward, coverage validation)
- Adds atomic commits after each stage for crash recovery
- Deprecates standalone research-project, define-requirements, create-roadmap
(kept for mid-project use)
Fixes from audit:
- Add requirements quality criteria (specific, user-centric, atomic, independent)
- Add milestone context to research prompts (greenfield vs subsequent)
- Add quality gates per research dimension
- Add template references for consistent output format
Removes deprecated gsd-researcher.md (replaced by project/phase researchers)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove phantom status.md command (background agent model abandoned)
- Remove agent-history.md template (unused)
- Remove _archive/ directory
- Add narration to execute-phase (describe what's being built before/after waves)
- Update new-project to offer define-requirements as fast path
- Make define-requirements work without research (gather through questioning)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Follow threads naturally instead of rigid step order
- Cleaner question techniques in questioning.md
- Background context checklist instead of forced checklist mode
- Updated next steps to show research flow
Adds /gsd:research-project to research domain ecosystem before creating roadmap.
Spawns parallel agents to investigate stack, features, architecture, and pitfalls.
New files:
- commands/gsd/research-project.md
- get-shit-done/workflows/research-project.md
- get-shit-done/templates/research-project/ (5 templates)
Modified:
- new-project.md: offers research vs direct roadmap options
- create-roadmap.md: loads research if exists
- workflows/create-roadmap.md: uses research to inform phases
Co-Authored-By: Claude <noreply@anthropic.com>
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>
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>
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>
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>
- 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>
- 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>
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>
- 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.
- Removed roadmap_and_state step from new-project command
- new-project now offers research-project or create-roadmap as next steps
- Updated help.md with new 5-step Quick Start flow
- Documented research-project and create-roadmap commands in help
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
