| name | plan-writing |
| description | Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work. |
| allowed-tools | Read, Glob, Grep |
Plan Writing
Source: obra/superpowers
Overview
This skill provides a framework for breaking down work into clear, actionable tasks with verification criteria.
Task Breakdown Principles
1. Small, Focused Tasks
- Each task should take 2-5 minutes
- One clear outcome per task
- Independently verifiable
2. Clear Verification
- How do you know it's done?
- What can you check/test?
- What's the expected output?
3. Logical Ordering
- Dependencies identified
- Parallel work where possible
- Critical path highlighted
- Phase X: Verification is always LAST
4. Dynamic Naming Under Root Docs
- Plan files are saved under root
docs/, using the closest existing docs folder for the artifact type.
- Name derived from task (e.g., "add auth" ->
docs/plans/auth-feature.md, or a phase-specific file under docs/phases/[phase]/).
- NEVER place generated project-facing plans inside
.agent/, .codex/, .claude/, or temp folders unless the user explicitly asks.
Planning Principles (NOT Templates!)
🔴 NO fixed templates. Each plan is UNIQUE to the task.
Principle 1: Keep It SHORT
| ❌ Wrong | ✅ Right |
|---|
| 50 tasks with sub-sub-tasks | 5-10 clear tasks max |
| Every micro-step listed | Only actionable items |
| Verbose descriptions | One-line per task |
Rule: If plan is longer than 1 page, it's too long. Simplify.
Principle 2: Be SPECIFIC, Not Generic
| ❌ Wrong | ✅ Right |
|---|
| "Set up project" | "Run npx create-next-app" |
| "Add authentication" | "Install next-auth, create /api/auth/[...nextauth].ts" |
| "Style the UI" | "Add Tailwind classes to Header.tsx" |
Rule: Each task should have a clear, verifiable outcome.
Principle 3: Dynamic Content Based on Project Type
For NEW PROJECT:
- What tech stack? (decide first)
- What's the MVP? (minimal features)
- What's the file structure?
For FEATURE ADDITION:
- Which files are affected?
- What dependencies needed?
- How to verify it works?
For BUG FIX:
- What's the root cause?
- What file/line to change?
- How to test the fix?
Principle 4: Scripts Are Project-Specific
🔴 DO NOT copy-paste script commands. Choose based on project type.
| Project Type | Relevant Scripts |
|---|
| Frontend/React | ux_audit.py, accessibility_checker.py |
| Backend/API | api_validator.py, security_scan.py |
| Mobile | mobile_audit.py |
| Database | schema_validator.py |
| Full-stack | Mix of above based on what you touched |
Wrong: Adding all scripts to every plan
Right: Only scripts relevant to THIS task
Principle 5: Verification is Simple
| ❌ Wrong | ✅ Right |
|---|
| "Verify the component works correctly" | "Run npm run dev, click button, see toast" |
| "Test the API" | "curl localhost:3000/api/users returns 200" |
| "Check styles" | "Open browser, verify dark mode toggle works" |
Plan Structure (Flexible, Not Fixed!)
# [Task Name]
## Goal
One sentence: What are we building/fixing?
## Tasks
- [ ] Task 1: [Specific action] → Verify: [How to check]
- [ ] Task 2: [Specific action] → Verify: [How to check]
- [ ] Task 3: [Specific action] → Verify: [How to check]
## Done When
- [ ] [Main success criteria]
That's it. No phases, no sub-sections unless truly needed.
Keep it minimal. Add complexity only when required.
Notes
[Any important considerations]
---
## Decision Elicitation (Blocking Gates in the Plan)
> Full spec: `.agent/protocols/guidelines/21-decision-elicitation.md`
Before implementing a phase that has unresolved decisions, **insert a decision block inline** — immediately above the tasks it affects.
### MCQ Block (Technical Decisions)
Use for bounded choices with clear trade-off profiles (e.g., DB engine, auth strategy, rendering model).
[!IMPORTANT]
[Decision Label] — Choose one.
- A) [Option] — [Why it's a viable candidate]
- B) [Option] — [Why it's a viable candidate]
- C) [Option] — [Why it's a viable candidate]
❓ Kairou's lean: Option [X] — [architectural reason].
### Open-Ended Block (Contextual / Experiential Decisions)
Use for decisions that depend on user knowledge, team conventions, or existing infrastructure.
[!NOTE]
[Decision Label] — Your context shapes the answer here.
[Framing — what is Kairou trying to understand?]
❓ Example answers: "[A]" / "[B]" / "No preference"
### Plan Status Annotation (Header)
Every plan artifact with pending decisions must have this at the top:
[!WARNING]
Plan Status: PENDING DECISIONS — X questions require your input before implementation begins.
Change to `[!TIP] Plan Status: READY` once all decisions are answered.
**Rules:**
- Max 3 decision blocks per phase. Collapse minor ones into a table.
- MCQ: always 2–4 options. Always include Kairou's lean.
- Open-ended: always include example answers.
- Decisions go BEFORE the tasks that depend on them, not at the end.
---
## Best Practices (Quick Reference)
1. **Start with goal** - What are we building/fixing?
2. **Max 10 tasks** - If more, break into multiple plans
3. **Each task verifiable** - Clear "done" criteria
4. **Project-specific** - No copy-paste templates
5. **Update as you go** - Mark `[x]` when complete
---
## When to Use
- New project from scratch
- Adding a feature
- Fixing a bug (if complex)
- Refactoring multiple files
