Skip to content
Agentmart
Submit a tool

plan

Turn settled requirements into an implementation plan with exact files, interfaces, tests, verification, and safe commit boundaries.

Skill by Rafcin

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/rafcin-plan

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Turn settled requirements into an implementation plan with exact files, interfaces, tests, verification, and safe commit boundaries.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/plan

What's inside

Skill name
plan
Description
Turn settled requirements into an implementation plan with exact files, interfaces, tests, verification, and safe commit boundaries.
License
MIT
Instructions
29 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Plan

## Entry conditions

Use after requirements are settled for multi-step, delegated, persistent, or risky work. If a business decision or acceptance criterion is still material and unresolved, return to `context` rather than hiding it in an assumption. Inspect instructions, architecture, callers, tests, configuration ownership, and the working tree.

## Scope limit

Write only the smallest executable plan for the accepted outcome. Preserve concurrent edits; do not use planning to make a material architecture or compatibility decision that belongs in `codebase-design` or needs approval. Each coherent vertical slice names:

- exact files to create, modify, or remove;
- public interfaces and data contracts;
- a failing behavior test to write first and its expected failure;
- the minimal implementation needed to make it pass;
- focused and baseline verification commands;
- ownership, rollback, security, or migration constraints;
- a focused commit boundary.

Call out dependencies, irreversible or external effects, secrets boundaries, and approval-gated verification. Separate source, local-runtime, and external-environment proof.

## Exit evidence

End with measurable acceptance criteria, ownership, an ordered task list, verification commands and expected results, and commit boundaries. The plan must make no unapproved external action look routine.

## Next gate

Hand a settled bounded slice to `tdd` and `implement`; retain it under `omcs` when it requires a declared agent packet or risk-gated review.

From Rafcin/oh-my-codex-slim, MIT.

More from Rafcin/oh-my-codex-slim

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 26, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Rafcin

Cite this page

plan skill. Agent Mart. https://agentmart.dev/skills/rafcin-plan (last updated 2026-10-24)