New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Cp Plan

by tangziwen in tangziwen/CubeMiniGame

Create or update a CodePlan design.md from clarified requirements, repository observations, constraints, and architecture intent.

MITAuto-check passedFrontend & Design

Install Cp Plan

skills CLI
$ npx skills add tangziwen/CubeMiniGame --skill cp-plan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install tangziwen/CubeMiniGame cp-plan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/tangziwen/CubeMiniGame.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cp-plan .claude/skills/cp-plan && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cp-plan
GitHub stars
359
Token cost
~928 tokens
SKILL.md length
452 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Create or update a CodePlan design.md from clarified requirements, repository observations, constraints, and architecture intent.

  • Works in 4 steps: Summarize what already exists. → Ask what the user wants to change,… → Preserve stable design decisions unless… → …
  • Explicitly asks to write
  • SKILL.md covers Shared Contract, Purpose, Idempotency and Readiness Gate, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Cp Plan is an agent skill from tangziwen/CubeMiniGame. Create or update a CodePlan design.md from clarified requirements, repository observations, constraints, and architecture intent. Use after cp-explore or when the user explicitly asks to write, update, or refine the high-level CodePlan design.

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Frontend & Design, covering Design tokens. The repository describes itself as: HomeBrew C++ 3D Game Engine based on OpenGL & Vulkan. The licence is MIT.

When your agent uses it

  • Explicitly asks to write
  • Refine the high-level CodePlan design

Example prompts

  • “/cp-plan”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Summarize what already exists.
  2. Ask what the user wants to change, clarify, or extend.
  3. Preserve stable design decisions unless the user explicitly replaces them.
  4. If step*.md already exists, warn that updating design.md may make the steps stale and should be followed by cp-refine.

What it can do on your machine

Read from SKILL.md and the folder at commit 33b364c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cp Plan loads about 928 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 452 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~928

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from tangziwen/CubeMiniGame at commit 33b364c, republished under its MIT licence (© tangziwen). 452 words, ~928 tokens.

Download SKILL.mdSave it as .claude/skills/cp-plan/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
cp-plan
description
Create or update a CodePlan design.md from clarified requirements, repository observations, constraints, and architecture intent. Use after cp-explore or when the user explicitly asks to write, update, or refine the high-level CodePlan design.
disable-model-invocation
true

CodePlan Plan

Shared Contract

Before acting, read ../_shared/codeplan/core.md.

Purpose

Create or update CodePlan/<PlanName>/design.md. Capture durable requirements, constraints, current state, target architecture, coarse phases, risks, and validation strategy.

Do not create stepX.md files or implement code while planning unless the user explicitly changes the task.

Idempotency

If the target plan already has design.md, do not silently overwrite it.

Before updating an existing design.md:

  1. Summarize what already exists.
  2. Ask what the user wants to change, clarify, or extend.
  3. Preserve stable design decisions unless the user explicitly replaces them.
  4. If step*.md already exists, warn that updating design.md may make the steps stale and should be followed by cp-refine.

Readiness Gate

Before creating or updating design.md, verify that the request is clear enough to become a CodePlan.

Do not write design.md when the user's requirement is only a short, broad, or ambiguous wish such as "help me implement a spaceship simulator" or "make the engine better".

A request is not ready when important information is missing, such as:

  • target behavior or user-visible result
  • affected subsystem or likely repository area
  • hard constraints, compatibility expectations, or non-goals
  • whether old behavior should be preserved, replaced, or deprecated
  • enough context to estimate the CodePlan scope

If the request is not ready:

  1. Stop before creating or editing design.md.
  2. Ask only the clarifying questions that materially affect the plan.
  3. Recommend using cp-explore when the user needs discovery before planning.
  4. Offer a compact candidate CodePlan name only if enough direction is already visible.
Show full SKILL.md (202 more words)Show less

Workflow

  1. Read project instructions, especially AGENTS.md.
  2. Resolve the target CodePlan directory.
  3. Inspect related existing CodePlan documents for style and continuity.
  4. Gather requirements, constraints, open questions, and relevant repository facts.
  5. Apply the readiness gate and stop if the request is not clarified enough.
  6. Apply the shared scope gate from core.md and stop with split suggestions if the plan is too large.
  7. Create or update design.md.
  8. Keep implementation details at architecture level.
  9. Leave file-by-file execution details for cp-refine.

Design Shape

Use this exact English heading shape by default:

md
# <Readable Plan Title>

## Requirements

## Notes

## Current State

## Core Problem

## Target Architecture

## Overall Route

## Phases

## Key Risks

## Validation Strategy

## Validation Status

Coarse architecture-level phases belong in design.md. Detailed file operations belong in stepX.md.

The last phase in Phases must always be a validation phase. By default, validation is text-level or static verification: review the design against requirements and non-goals, inspect code symbols and paths, verify planned file scope, and check that later stepX.md files stay within the plan. Do not make compilation the default validation method unless the user explicitly asks for it.

Context Budget

Write design.md so implementation agents only need:

  • design.md
  • progress.md
  • the current stepX.md

Avoid requiring all step files to understand the overall design.

Do not instruct agents to compile unless the user explicitly asks.

© tangziwen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/cp-plan of tangziwen/CubeMiniGame.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 33b364c

Compare with similar skills

Cp Plan next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cp Plan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cp Plan this skilltangziwen/CubeMiniGame359—~928Automated safety check: PassMIT
Figma Design System Builderwarpdotdev/warp65k2 repos~4.4kAutomated safety check: PassAGPL-3.0
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
MCP Developmentcoollabsio/coolify63k1 repos~949Automated safety check: PassMIT
Design SystemOhh-889/skyroc79511 repos~1.7kAutomated safety check: PassMIT
Design Dnazanwei/design-dna1.9k1 repos~2.1kAutomated safety check: PassMIT

Similar skills

  • Figma Design System Builder

    warpdotdev/warp

    Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.

    65k GitHub starsUsed in 2 repos~4.4k tokens
    Frontend & DesignAuto-check passed

  • Figma use_figma Plugin API Rules

    warpdotdev/warp

    Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed

  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed

  • Design System

    Ohh-889/skyroc

    Token architecture, component specifications, and slide generation.

    795 GitHub starsUsed in 11 repos~1.7k tokens
    Frontend & DesignAuto-check passed

  • Design Dna

    zanwei/design-dna

    Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects…

    1.9k GitHub starsUsed in 1 repo~2.1k tokens
    Frontend & DesignAuto-check passed

  • Figma Design to Code

    warpdotdev/warp

    Turns a Figma frame or component into production code that matches the design, using the Figma MCP server and the project's own design system.

    65k GitHub starsUsed in 4 repos~2.9k tokens
    Frontend & DesignAuto-check passed

More from tangziwen/CubeMiniGame

All 12 skills in this repo

  • Build Project

    tangziwen/CubeMiniGame

    Build the project using the CMake presets defined for this repository.

    359 GitHub stars~407 tokensUpdated 21 days ago
    Auto-check passed

  • Cp Apply

    tangziwen/CubeMiniGame

    Apply exactly one CodePlan step to the repository, with preflight idempotency checks and progress.md updates.

    359 GitHub stars~566 tokensUpdated 21 days ago
    Auto-check passed

  • Cp Explore

    tangziwen/CubeMiniGame

    Explore and clarify a prospective CodePlan before writing design.md.

    359 GitHub stars~535 tokensUpdated 21 days ago
    Auto-check passed

  • Cp Refine

    tangziwen/CubeMiniGame

    Refine a CodePlan design.md into precise step1.md through stepX.md files and progress.md.

    359 GitHub stars~512 tokensUpdated 21 days ago
    Auto-check passed

  • Cp Review

    tangziwen/CubeMiniGame

    Review CodePlan documents, including explored requirements, design.md, progress.md, and step files.

    359 GitHub stars~475 tokensUpdated 21 days ago
    Auto-check passed

  • Engine Codemap Sync

    tangziwen/CubeMiniGame

    Assess whether completed engine code changes should be reflected in Doc/EngineCodeMap.

    359 GitHub stars~936 tokensUpdated 21 days ago
    Auto-check passed

Categories

Questions about Cp Plan

What does Cp Plan do?

Create or update a CodePlan design.md from clarified requirements, repository observations, constraints, and architecture intent. Cp Plan is an agent skill from tangziwen/CubeMiniGame.md from clarified requirements, repository observations, constraints, and architecture intent.

When should I use Cp Plan?

Cp Plan fits situations like: explicitly asks to write; refine the high-level CodePlan design.

How do I install Cp Plan in Claude Code?

Run `npx skills add tangziwen/CubeMiniGame --skill cp-plan -a claude-code`. Or copy the skill folder (.agents/skills/cp-plan in tangziwen/CubeMiniGame) into .claude/skills/cp-plan in your project. Claude Code loads it when a task matches its description.

How do I install Cp Plan in Codex?

Run `npx skills add tangziwen/CubeMiniGame --skill cp-plan -a codex`. Or copy the skill folder (.agents/skills/cp-plan in tangziwen/CubeMiniGame) into .agents/skills/cp-plan in your project. Codex loads it when a task matches its description.

Can I use Cp Plan in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tangziwen/CubeMiniGame --skill cp-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cp-plan, .gemini/skills/cp-plan, .github/skills/cp-plan and .opencode/skills/cp-plan in your project.

What does Cp Plan need to run?

SKILL.md names no scripts, command-line tools or credentials: Cp Plan is instructions for the agent only.

Does Cp Plan access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cp Plan safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cp Plan use?

Cp Plan is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cp Plan use?

About 928 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cp Plan?

Skills that share tags, products or a category with Cp Plan: Figma Design System Builder (warpdotdev/warp, 65k stars), Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars), MCP Development (coollabsio/coolify, 63k stars) and Design System (Ohh-889/skyroc, 795 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cp Plan?

tangziwen (a GitHub user) maintains it in tangziwen/CubeMiniGame, which has 359 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 19, 2026.

Source: tangziwen/CubeMiniGame on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.