# Plan Before Execution

> Create a bounded plan before non-trivial work. Use for multi-file, high-risk, ambiguous, or delegated work.

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

---


# Plan Before Execution

## Purpose
Create a bounded plan before non-trivial work.

## When to Use
Use for multi-file, high-risk, ambiguous, or delegated work.

## Inputs
Goal, scope, constraints, source files, risks, verification options.

## Steps
1. Restate the goal.
2. Define in-scope and out-of-scope work.
3. Split execution into reviewable phases.
4. Attach verification to each risky phase.

## Gates
The plan covers the user request, constraints, blockers, and checks.

## Evidence
An actionable plan or checklist exists before implementation.

## Anti-Patterns
Editing first and discovering scope later; treating a plan as approval.

## Related
`scope-and-blockers`, `assumption-registry`