Lifecycle management of plan documents from creation to automatic cleanup after merge. Use when creating, referencing, or cleaning up plans.
Manages feature plan documents through their lifecycle: creates `.plan/feature_plan.md` files when you start new work, and automatically deletes only the merged feature's plan after `git merge` completes, preserving other concurrent work plans.
/plugin marketplace add binee108/nine-step-workflow-plugin/plugin install nine-step-workflow@lilylab-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Creation → Active → Cleanup
.plan/{{feature_name}}_plan.mdrm .plan/{{feature_name}}_plan.mdDelete: Merged feature's plan only Preserve: Concurrent work plans Protection: Never delete other plans
# Before merge
ls .plan/
# feature-a_plan.md
# feature-b_plan.md
# Merge feature-a complete
rm .plan/feature-a_plan.md
# After
ls .plan/
# feature-b_plan.md ← Preserved
Create plan
↓
Phases reference plan
↓
Merge complete
↓
Delete plan (cleanup Step 1)
Recommended sections:
# {{Feature Name}} Implementation Plan
## Overview
- Purpose: {{Why this feature}}
- Scope: {{What's included/excluded}}
- Dependencies: {{Required features/systems}}
## Phases
### Phase 1: {{Phase Name}} ({{Estimated Time}})
**Deliverable:** {{What gets built}}
**Test Criteria:** {{How to verify}}
**Success Criteria:**
- [ ] {{Criterion 1}}
- [ ] {{Criterion 2}}
### Phase 2-N: ...
(Repeat structure)
## Risk Assessment
- **{{Risk Type}}**: {{Description}} → Mitigation: {{Strategy}}
## Architecture Changes
- {{Component}}: {{Change description}}
## Security Considerations
- {{Concern}}: {{How addressed}}
## Testing Strategy
- Unit tests: {{Coverage}}
- Integration tests: {{Scenarios}}
- Performance tests: {{Criteria}}
## Rollback Plan
- {{How to undo changes if needed}}
Scenario: Multiple teams/features in parallel
# Team A working on feature-x
.plan/feature-x_plan.md
# Team B working on feature-y
.plan/feature-y_plan.md
# Team C working on bug-fix-z
.plan/bug-fix-z_plan.md
# Team A merges feature-x
rm .plan/feature-x_plan.md ← Only delete this one
# Teams B and C continue working
ls .plan/
# feature-y_plan.md
# bug-fix-z_plan.md
Immutability Principle: Plans should remain largely unchanged after Step 2.5 approval.
When updates are allowed:
Format for updates:
## Updates Log
### {{Date}} - {{Reason}}
- {{What changed}}
- {{Why it changed}}
- User approval: {{Yes/No}}
When NOT to update:
Instead: Document deviations and get user approval if significant
For detailed lifecycle, see reference.md For more examples, see examples.md
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.