plan-first

---
name: plan-first
description: Use for any coding task with more than about three steps or touching more than one file — new features, refactors, migrations, multi-file changes, or vague requests like "build X" or "add Y to the app". Read the code, write a short plan, then execute step by step with checks.
---

# Plan First

Long tasks fail when you start editing before you understand the code. Plan briefly, then execute.

## 1. Load context (before writing any code)
- `mem_context`, then `mem_search` with the feature/module name — reuse past decisions and known pitfalls.
- Read the files you will touch **and** one or two similar existing features. Copy their patterns.
- Identify: entry point, data flow, where tests live, how the project is run.

## 2. Clarify only what blocks you
If a choice changes the result and cannot be inferred from the code (e.g. which database, breaking an API),
ask one short question. Otherwise pick the option most consistent with the codebase and state it.

## 3. Write the plan (keep it short)
```
Goal: <one sentence>
Steps:
1. <small, verifiable change> — check: <how you will know it worked>
2. ...
Risks: <what could break>
```
Each step should be small enough to verify on its own. Prefer 3–7 steps.

## 4. Execute one step at a time
- Do step N → run its check → only then move to step N+1.
- If a check fails, fix it before continuing. Do not pile new changes on a broken state.
- If you discover the plan is wrong, stop, update the plan, and say what changed.

## 5. Stay in scope
- Do not refactor, rename, or "improve" code the task did not ask for.
- Match the existing style, naming, and libraries. Do not add a dependency if the project already has one that does the job.

## 6. Finish
- Run the full verification (see the `verify-before-done` skill).
- Save architecture/design decisions with `mem_save` (What / Why / Where / Lesson).
- Report: what was done, what was verified, what is left.