- Debug files from UAT use same naming as regular debug (slug only)
- UAT.md tracks link via debug_session field
- plan-fix actually invokes execute-plan when user selects it
Co-Authored-By: Claude <noreply@anthropic.com>
Diagnosis always produces better fixes and runs in parallel anyway.
Removing the prompt reduces cognitive load.
Co-Authored-By: Claude <noreply@anthropic.com>
After UAT finds issues, spawn parallel debug agents to investigate
root causes before planning fixes. Each agent investigates one issue
with symptoms pre-filled from UAT, finds the root cause, and returns
diagnosis.
New files:
- workflows/diagnose-issues.md: Orchestrator for parallel debug agents
- templates/debug-subagent-prompt.md: Prompt template for debug subagents
Modified:
- workflows/debug.md: Add symptoms_prefilled and diagnose-only modes
- workflows/verify-work.md: Offer diagnosis step after issues found
- templates/UAT.md: Add root_cause and debug_session fields
- commands/gsd/plan-fix.md: Use root causes for targeted fix planning
Flow: UAT → diagnose (parallel) → plan-fix (with root causes) → execute
Co-Authored-By: Claude <noreply@anthropic.com>
- One test at a time instead of full checklist upfront
- Plain text responses instead of AskUserQuestion forms
- Severity inferred from description, never asked
- Persistent UAT.md survives /clear (like debug workflow)
- Single file per phase replaces per-plan ISSUES.md
- Updated plan-fix to read from UAT.md
Co-Authored-By: Claude <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>
- Fix brownfield example to use execute-phase instead of execute-plan
- Remove /gsd:resume-task command (relies on broken Task resume)
- Checkpoint continuation now uses fresh agents, not resume
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
execute-phase with parallel agents is the recommended path.
execute-plan is for single-plan or interactive checkpoint handling.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Resume fails when subagents use parallel tool calls due to Claude Code
serialization bug (consecutive assistant entries with same message ID).
Solution: Subagents return structured checkpoint state, orchestrator
spawns fresh agent with continuation-prompt template instead of resuming.
New files:
- templates/checkpoint-return.md: Structured format with completed tasks table
- templates/continuation-prompt.md: Template for spawning continuation agent
Updated:
- templates/subagent-task-prompt.md: Reference checkpoint-return, remove resume language
- workflows/execute-phase.md: Replace Task(resume=id) with fresh agent spawn
- workflows/execute-plan.md: Update checkpoint_return_for_orchestrator step
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
execute-plan.md command now spawns subagent instead of executing directly:
- Loads only subagent-task-prompt template (~100 lines vs ~2200)
- Subagent loads full execute-plan workflow, summary, checkpoints, tdd
- Handles checkpoint returns with resume flow
- ~80% context reduction for orchestrator
Also updated subagent-task-prompt.md description to clarify it's used by
both execute-phase (parallel) and execute-plan (single) orchestrators.
Co-Authored-By: Claude <noreply@anthropic.com>
Scope boundaries are implicit from the roadmap. Asking about them
creates the sensation of scope creep and interrogates the user about
constraints they didn't mention.
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>
- execute-plan.md: Add checkpoint_return_for_orchestrator step
explaining how to return at checkpoints when spawned via Task tool
- subagent-task-prompt.md: Add checkpoint_behavior and completion_format
sections to guide agents on returning for checkpoints
Tested: Task resume works - agent pauses at checkpoint, returns with
details, orchestrator presents to user, resumes with Task(resume=id).
Parallel agents each get unique agent_id for independent resume.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Shows table of all active debug sessions with status/hypothesis/next action
- Reply with number to resume, or describe new issue
- No AskUserQuestion for session selection - inline flow
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Clarified verification instructions for usage.
I was initially trying to get this to work in my PowerShell terminal, but later realized that the /gsd:help command became available inside Claude Code.
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>
New features:
- /gsd:execute-phase: run all plans in a phase with parallel background agents
- /gsd:status: monitor background agent status from parallel execution
- Parallelization-aware planning with depends_on and files_modified frontmatter
- Automatic dependency analysis and wave-based execution
Configuration options in .planning/config.json:
- max_concurrent_agents (default: 3)
- skip_checkpoints (default: true)
- min_plans_for_parallel (default: 2)
Inspired by PR #43 from @davesienkowski - thank you for the design work!
