Is the CC Agent Design skill free?

Yes. The skill itself is free from cablate/ai-toolkit. SkillProof publishes the install command and an independent test verdict at no cost.

What is the CC Agent Design SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install CC Agent Design?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use CC Agent Design with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

CC Agent Design

Reverse-engineered Claude Code built-in agent configs (tools, model routing, omitClaudeMd) turned into a design checklist for your own subagents.

by cablate · cablate/ai-toolkit

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 5f00691

Its central claim — reverse-engineered built-in-agent configs — checks out against ground truth: this very session's own Explore and Plan agent tool-lists ('All tools except Agent, Artifact, ExitPlanMode, Edit, Write, NotebookEdit') match the skill's documented disallowedTools almost exactly, which is unusually strong corroboration for a third-party 'reverse-engineering' claim. Entire skill body and description are in Traditional Chinese, which won't block Claude from using it but is a real readability barrier for most catalog users.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What CC Agent Design does

A design guide for configuring Claude Code subagents, derived from analysis of Claude Code's own 6 built-in agents (general-purpose, Explore, Plan, verification, claude-code-guide, statusline-setup) — covering tool minimization, model-tier selection, omitClaudeMd usage, and dispatch-prompt writing with concrete good/bad examples. Triggers on designing a new agent, optimizing an agent's system prompt, deciding tool/model configuration, or writing a dispatch prompt. Written in Traditional Chinese.

How to install CC Agent Design

git clone https://github.com/cablate/ai-toolkit
cd ai-toolkit
mkdir -p ~/.claude/skills
cp -r domain-skills/claude-code/cc-agent-design ~/.claude/skills/cc-agent-design

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger CC Agent Design

/cc-agent-design Reverse-engineered Claude Code built-in agent configs (tools, model routing, omitClaudeMd) turned into a design checklist for your own subagents.

It also activates on plain-language prompts like these:

我想設計一個唯讀的資料庫遷移審查子代理,該給它哪些工具、用哪個模型比較合適,幫我列出來?
幫我寫一個新子代理的系統提示詞和呼叫用的dispatch prompt,要精簡但完整清楚
這個子代理的工具清單要不要加Edit權限,還是保持唯讀比較安全,怎麼決定比較好?

Frequently asked questions

Is the CC Agent Design skill free?: Yes. The skill itself is free from cablate/ai-toolkit. SkillProof publishes the install command and an independent test verdict at no cost.
Does CC Agent Design work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Its central claim — reverse-engineered built-in-agent configs — checks out against ground truth: this very session's own Explore and Plan agent tool-lists ('All tools except Agent, Artifact, ExitPlanMode, Edit, Write, NotebookEdit') match the skill's documented disallowedTools almost exactly, which is unusually strong corroboration for a third-party 'reverse-engineering' claim. Entire skill body and description are in Traditional Chinese, which won't block Claude from using it but is a real readability barrier for most catalog users.
What is the CC Agent Design SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install CC Agent Design?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use CC Agent Design with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.