Karpathy Planning

---
name: karpathy-planning
description: Develop a scoped implementation plan when explicitly asked to plan a coding task. Use grill-me for a deliberate design interview.
disable-model-invocation: true
---

# karpathy-planning

Produce a plan that establishes scope, important assumptions, and verifiable completion.
Include only the detail needed to choose an approach and carry out the task.

- Resolve material ambiguities from available context. Ask when an answer would change the outcome; otherwise state a reasonable assumption.
- Prefer the simplest design that meets the request. Identify existing components to reuse and preserve unrelated work.
- Pair success criteria with relevant verification. Complete required checks; broaden testing only for changes, failures, or unresolved concerns.
- Describe substantial tradeoffs, dependencies, or irreversible steps when they matter.
- Match the output to the task. A four-part template and a repository-wide survey are not prerequisites to coding.
- If implementation is already authorized, proceed once blocking decisions are resolved; planning alone is not completion.

Adapted from [multica-ai/andrej-karpathy-skills](https://github.com/multica-ai/andrej-karpathy-skills).