Research is now integrated into /gsd:plan-phase by default.
Remove standalone research command from "Also available" sections.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds SessionStart hook that checks npm in background, caches result.
Statusline shows "⬆ /gsd:update │" when update available.
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>
- Analyze phase to identify gray areas by category (UI, UX, Behavior, etc.)
- Present multi-select for user to choose which areas to discuss
- Deep-dive each selected area with focused questioning loop
- Explicit scope guardrail: clarify HOW, never expand WHAT
- Capture deferred ideas without acting on them
- Downstream awareness: CONTEXT.md feeds researcher and planner agents
- Template restructured for decisions (domain, decisions, discretion, deferred)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Split gsd-researcher into two specialized agents:
- gsd-phase-researcher: tailored for phase research before planning
- gsd-project-researcher: tailored for ecosystem research before roadmap
Updated /gsd:plan-phase to auto-research before planning:
- Research runs if no RESEARCH.md exists (silent use if exists)
- --research flag forces re-research
- --skip-research flag bypasses research entirely
- Researchers commit their output
This enables single-command workflow: /gsd:plan-phase does
research → plan → verify in one orchestrated flow.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Plans created (PLANNING COMPLETE or CHECKPOINT handled)
- gsd-plan-checker spawned (unless --skip-verify)
- Verification passed OR user override OR max iterations with user decision
- User sees status between agent spawns
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Steps 1-7: Validate, parse, spawn planner (existing flow)
- Step 8: Spawn gsd-plan-checker with verification_context
- Step 9: Handle checker return (passed | issues)
- Step 10: Revision loop (max 3 iterations)
- Step 11: Present final status with verification outcome
User sees ping-pong between planner and checker in main context.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove context: fork (orchestrator stays in main context)
- Add --skip-verify flag to argument-hint
- Add Task tool to allowed-tools for spawning checker
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds context: fork and agent: general-purpose to plan-phase command.
This isolates the heavy discovery/synthesis work in a fresh 200k context
window, keeping the main conversation clean.
Removes AskUserQuestion from allowed-tools (workflow doesn't use it).
research-phase.md:
- Added <key_insight> framing ("what don't I know that I don't know")
- Added <downstream_consumer> explaining plan-phase integration
- Added <quality_gate> checklist
research-project.md:
- Added milestone context (greenfield vs v1.1+)
- Added <downstream_consumer> per dimension
- Added <quality_gate> per agent
- Enhanced roadmap implications guidance
gsd-researcher.md:
- Simplified <gsd_integration> to point to orchestrator-provided context
- Agent is now pure research capability, context is injected
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Reduces context exhaustion during /gsd:map-codebase by having agents
write documents directly instead of returning findings to orchestrator.
- Create gsd-codebase-mapper agent with embedded templates
- Agent understands downstream consumers (plan-phase, execute-plan)
- Parameterized by focus: tech, arch, quality, concerns
- Each focus writes specific documents directly to .planning/codebase/
- Orchestrator receives only confirmation + line counts
Context savings: ~40 lines returned vs potentially thousands of lines
of exploration findings previously transferred back to orchestrator.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The context section now includes @.planning/MILESTONE-CONTEXT.md so
Claude actually loads the file from discuss-milestone instead of just
seeing a text mention in the process steps.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Reduce from ~540 lines (command + workflow) to 130 lines
- Delegate research methodology to gsd-researcher agent
- Keep phase validation, context gathering in orchestrator
- Add spawn and continuation patterns for agent
- Reduced from 202 lines to 149 lines
- Removed workflow/reference loading (expertise now in agent)
- Uses subagent_type="gsd-debugger" instead of "general-purpose"
- Keeps symptom gathering and checkpoint handling in orchestrator
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>
Write to file only on: issue found, every 5 passes, or completion.
Eliminates wasteful I/O while maintaining reasonable crash recovery.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Match new-project format — both research-project and define-requirements
shown as equal paths with guidance on when to use each.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When ROADMAP.md is missing but PROJECT.md exists (after complete-milestone),
progress now correctly routes to /gsd:discuss-milestone instead of suggesting
new-project.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase completion commit now stages VERIFICATION.md alongside ROADMAP.md,
STATE.md, and REQUIREMENTS.md so verification results are tracked.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Milestone audit now reads existing VERIFICATION.md files from phases
(already created during execute-phase) rather than spawning verifiers
again. Aggregates tech debt and deferred gaps, then runs integration
checker for cross-phase wiring. Adds tech_debt status for non-blocking
accumulated debt.
Also adds VERIFICATION.md to phase completion commit in execute-phase.
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>
Sync execute-plan command and workflow with improved checkpoint display:
- Box header with ╔═══╗ for visual prominence
- Progress indicator at top
- Separator line before unmissable "→ YOUR ACTION:" prompt
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The when_to_use section was overly restrictive, refusing research
for "standard" domains. Research benefits any unfamiliar territory,
not just niche technical domains.
Co-Authored-By: Claude <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>
When execute-plan completes the last plan in a phase (summaries = plans),
it now spawns gsd-verifier to verify phase goal achievement before
proceeding to next phase.
Same verification flow as execute-phase, ensuring consistent behavior
regardless of which command is used.
Co-Authored-By: Claude <noreply@anthropic.com>
Deleted:
- subagent-task-prompt.md (baked into gsd-executor)
- subagent-verify-prompt.md (baked into gsd-verifier)
- continuation-prompt.md (baked into gsd-executor)
- checkpoint-return.md (baked into gsd-executor)
Co-Authored-By: Claude <noreply@anthropic.com>
- gsd-verifier.md: dedicated verification subagent with all logic baked in
- Goal-backward verification: checks codebase, not SUMMARY claims
- Creates VERIFICATION.md, returns status to orchestrator
- execute-phase spawns gsd-verifier instead of general-purpose
Co-Authored-By: Claude <noreply@anthropic.com>
- execute-plan.md: spawn gsd-executor instead of general-purpose with template
- execute-phase.md: spawn gsd-executor for wave-based parallel execution
- Remove template filling, subagent has all logic baked in
Co-Authored-By: Claude <noreply@anthropic.com>
ROADMAP.md, STATE.md, and REQUIREMENTS.md updates now commit
together as phase completion instead of separate commits.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Research now loads concrete requirements (e.g., "AUTH-02: User receives
email verification") to inform research domains, not just high-level
roadmap descriptions.
Co-Authored-By: Claude <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>
Promote /gsd:whats-new and update command visibility.
GSD evolves fast — users should check periodically.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Subagents can't determine if phase is complete. The orchestrator
(execute-plan and execute-phase commands) runs in main context,
can count plans vs summaries, and updates REQUIREMENTS.md when
phase completes.
- execute-plan: Step 2.5 updates requirements when summaries = plans
- execute-phase: Step 6 updates requirements (phase always complete)
- Removed duplicate from workflow (subagent can't run it anyway)
- Roadmap template now includes Requirements: field for each phase
- plan-phase loads REQUIREMENTS.md and extracts phase-specific requirements
- define-requirements shows full list inline before commit (not just counts)
