# Plan Writing

> Transform research findings into actionable implementation plans with stakes-based rigor, test-first strategy, and granular task decomposition.

- Skill: `a5c-ai/plan-writing` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add a5c-ai/plan-writing`
- Raw SKILL.md: https://api.skillmd.com/api/skills/a5c-ai/plan-writing/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: a5c-ai (https://skillmd.com/u/a5c-ai)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/a5c-ai/plan-writing

---


- Before implementing any medium or high stakes changes
- When requirements are clear and codebase is understood

## Process

1. **Load research** - Find `*-<topic>-research.md` in `docs/plans/`
2. **Classify stakes** - Low (isolated, reversible), Medium (multiple files), High (architectural)
3. **Define success criteria** - Functional, non-functional, and acceptance criteria
4. **Decompose tasks** - Granular steps with file paths, line references, verification methods
5. **Plan tests** - Test specification as first sub-step per task (test-first)
6. **Assess risks** - Breaking changes, performance, security, dependencies, rollback strategy
7. **Write plan document** - `docs/plans/YYYY-MM-DD-<topic>-plan.md`
8. **Approval gate** - Human approves, requests changes, or returns to research

## Anti-Patterns to Avoid

- Vague task descriptions without specific file references
- Missing verification criteria for any step
- Combining test writing and implementation into single steps
- Planning rigor mismatched to stakes level
- Proceeding without explicit user approval

## Tool Use

Invoke via babysitter process: `methodologies/rpikit/rpikit-plan`