MUST USE when creating executable plans, project roadmaps, or phase-based workflows. Creates Brief → Roadmap → Phases structure in .cattoolkit/planning/.
Creates hierarchical project plans (BRIEF → ROADMAP → phased PLANs) in `.cattoolkit/planning/` for autonomous execution. Use when building executable roadmaps for complex projects or quick task lists for simple work.
/plugin marketplace add Git-Fg/thecattoolkit/plugin install git-fg-thecattoolkit@Git-Fg/thecattoolkitThis skill is limited to using the following tools:
assets/templates/adr-entry.mdassets/templates/issue-entry.mdassets/templates/lite-plan.mdreferences/authentication-gates.mdreferences/checkpoints.mdreferences/cli-automation.mdreferences/context-management.mdreferences/domain-expertise.mdreferences/git-integration.mdreferences/hierarchy-rules.mdreferences/milestone-management.mdreferences/plan-format.mdreferences/research-pitfalls.mdreferences/scope-estimation.mdreferences/user-gates.mdtemplates/brief.mdtemplates/continue-here.mdtemplates/issues.mdtemplates/milestone.mdtemplates/phase-prompt.mdCreate hierarchical project plans with fresh context for autonomous execution.
Use the create workflow to:
This workflow provides step-by-step guidance with templates for creating executable plans that can be run with fresh context in autonomous sessions.
Use the edit workflow to:
Use the audit workflow to:
Single PLAN.md with 2-3 tasks for smaller projects.
Use when: Simple feature, quick task, focused work
Hierarchical structure with BRIEF.md + ROADMAP.md + phased PLAN.md files
Use when: Complex project, multiple phases, team coordination
.cattoolkit/planning/
└── {project-slug}/ # Scoped project folder (kebab-case)
├── BRIEF.md # Project vision, constraints, scope
├── ROADMAP.md # Architecture, phases, progress tracking
├── ADR.md # Architecture Decision Records (auto-created)
├── ISSUES.md # Deferred enhancements (auto-created)
└── phases/
├── {number}-{phase-name}/
│ ├── PLAN.md # Executable tasks for this phase
│ ├── SUMMARY.md # Phase summary
│ └── ...
└── ...
Workflow templates in templates/:
templates/brief.md - BRIEF.md templatetemplates/roadmap.md - ROADMAP.md templatetemplates/phase-prompt.md - Phase PLAN.md templatetemplates/summary.md - Phase summary templatetemplates/research-prompt.md - Research phase templatetemplates/milestone.md - Milestone completion templatetemplates/issues.md - ISSUES.md templatetemplates/continue-here.md - Handoff/continue templatePlan templates in assets/templates/:
assets/templates/lite-plan.md - Single PLAN.md for small projectsassets/templates/adr-entry.md - Architecture Decision Record entryassets/templates/issue-entry.md - Deferred enhancement entryWHY: Templates ensure plans follow consistent YAML frontmatter and structure patterns with proper state tracking.
Progress tracking uses non-destructive YAML frontmatter instead of filesystem renaming.
Each phase's PLAN.md includes frontmatter with status:
---
phase: 01-foundation
type: execute
status: in_progress # ← Tracks current state
---
Status values:
in_progress - Currently executingcompleted - Phase complete (all plans finished)The central ROADMAP.md serves as the single source of truth for project progress:
## Progress
| Phase | Plans Complete | Status | Completed |
|-------|----------------|--------|-----------|
| 1. Foundation | 3/3 | Complete | 2025-01-15 |
| 2. Authentication | 0/2 | Not started | - |
| 3. Core Features | 0/1 | Not started | - |
Benefits:
done_ prefixes break relative pathsAutonomous sessions start with ZERO context - every plan MUST:
@src/database/schema.tsInclude **[CHECKPOINT]** for:
When Rule 4 (Architectural Change) is approved during execution:
Create ADR entry in ADR.md:
## ADR-001: [Decision Title]
**Date:** YYYY-MM-DD
**Phase:** [Phase Name]
**Trigger:** Rule 4 - Architectural Change during [task name]
### Decision
[What was decided - concise statement]
### Context
**Current task:** [task name]
**Discovery:** [what prompted this]
**Proposed change:** [architectural modification]
### Rationale
[Why this decision was made]
### Alternatives Considered
[Other approaches evaluated]
### Consequences
**Positive:**
- [Expected benefits]
**Negative:**
- [Trade-offs or drawbacks]
**Impact:**
- [What this affects]
ADR Creation Protocol:
.cattoolkit/planning/{project-slug}/ADR.mdLog non-critical improvements for future phases:
## Open Enhancements
### ISS-001: [Brief description]
- **Discovered:** Phase [X] Plan [Y] Task [Z]
- **Type:** [Performance / Refactoring / UX / Testing]
- **Description:** [What could be improved]
- **Impact:** Low (works correctly, this would enhance)
- **Effort:** [Quick / Medium / Substantial]
Auto-increment from existing phases:
find .cattoolkit/planning/{project-slug}/phases -type d | wc -l
# Execution Context
Files to read before starting
# Tasks
Checkbox list of actions
# Checkpoints
Items with **[CHECKPOINT]** markers
# Success Criteria
Definition of done
references/plan-format.md - Detailed PLAN.md structurereferences/context-management.md - Context window managementreferences/scope-estimation.md - How to size plans appropriatelyreferences/checkpoints.md - Checkpoint types and usagereferences/cli-automation.md - What can be automated via CLIreferences/hierarchy-rules.md - Plan hierarchy and structure rulesreferences/authentication-gates.md - Handling authentication during executionreferences/user-gates.md - User interaction gatesreferences/milestone-management.md - Milestone trackingreferences/domain-expertise.md - Domain expertise considerationsreferences/research-pitfalls.md - Common research mistakesreferences/git-integration.md - Git workflow integrationThis 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.