# Plan

> Break ambiguous work into explicit, verifiable steps before implementation when the task is broad enough to benefit from a plan.

- Skill: `agentic-in/plan` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentic-in/plan`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentic-in/plan/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: agentic-in (https://skillmd.com/u/agentic-in)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/agentic-in/plan

---


# Plan

Use this skill when the task spans multiple files, behaviors, or validation steps.

## Preferred Flow

1. State the user-visible outcome.
2. Break the work into the smallest meaningful execution tracks.
3. Keep each step testable and tied to a concrete surface.
4. Re-plan when new evidence changes the execution path.

## Guardrails

- Do not spend time on a heavyweight plan for a one-file trivial edit.
- Keep plans actionable, not decorative.