Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/znlnzi/claude-config-studio/setupnpx skills add znlnzi/claude-config-studio --skill setupgit clone --depth 1 https://github.com/znlnzi/claude-config-studioWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/znlnzi/claude-config-studio/setup)<a href="https://agentmods.dev/skills/znlnzi/claude-config-studio/setup"><img src="https://agentmods.dev/badge/skills/znlnzi/claude-config-studio/setup.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00022 | $0.02409 |
| Opus 5 | $0.00011 | $0.01205 |
| Sonnet 5 | $0.00004 | $0.00482 |
| Haiku 4.5 | $0.00002 | $0.00241 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup -- 项目初始化与升级
根据项目特征自动推荐配置。新项目走完整初始化流程，已配置项目走增量升级流程。
模式判断
根据项目状态自动选择模式：
| 条件 | 模式 | 行为 |
|---|---|---|
无 .claude/ 目录 |
全新初始化 | 检测项目 → 3 个问题 → 安装模板 → 写 meta |
有 .claude/ + 无 .setup-meta.json |
注册现有配置 | 扫描已有配置 → 问用户偏好 → 写 meta（不改已有内容） |
有 .setup-meta.json 或传 --upgrade |
增量升级 | 对比已安装 vs 可用 → 展示新功能 → 用户选择性添加 |
传了 --reset |
重新配置 | 备份 → 重走完整流程 |
模式 A: 全新初始化（无 .claude/）
1. 检测项目特征（自动，零操作）
调用 detect_project 工具，传入当前项目路径。该工具一次调用即返回完整的项目特征：
- 语言/框架: 自动识别（TypeScript, Go, Python, Rust 等）
- 测试框架: 从依赖和配置文件中提取（Jest, Vitest, pytest, go test 等）
- 包管理器: 通过 lock 文件优先匹配（pnpm, yarn, npm, poetry 等）
- Git 状态: 是否初始化、最近作者（判断独立/团队）、当前分支
- Claude 配置:
.claude/目录和.setup-meta.json状态（可直接用于模式判断）
返回结果中的 claude_config 字段可直接用于模式判断：
has_claude_dir == false→ 模式 A（全新初始化）has_claude_dir == true && has_setup_meta == false→ 模式 B（注册现有配置）has_setup_meta == true→ 模式 C（增量升级）
简洁呈现检测结果：
我快速扫描了一下：
- 项目类型: Next.js 14 + TypeScript
- 测试框架: Jest + React Testing Library
- 包管理器: pnpm
- Git: 已初始化，最近 3 个 commit 都是同一作者
2. 快速配置（严格控制在 3 个问题以内）
使用 AskUserQuestion 工具，一次性问 3 个问题：
问题 1: 开发风格偏好
- (a) 严谨型 -- TDD、代码审查、严格类型检查（推荐给生产项目）
- (b) 快速型 -- 重速度，轻流程（推荐给原型/实验/hackathon）
- (c) 平衡型 -- 关键路径严谨，其余灵活
问题 2: 团队规模
- (a) 独立开发（根据 git log 判断是否只有一个作者，如果是则标注 [检测到]）
- (b) 团队协作
问题 3: 跨会话记忆
- (a) 启用（推荐）-- Claude 记住上次聊到哪里、你的偏好、项目知识
- (b) 不需要
3. 配置映射与安装
根据选择调用 MCP 工具安装模板：
| 选择组合 | 安装的模板 | 核心能力 |
|---|---|---|
| 严谨 + 独立 + 记忆 | hackathon-core + cross-session-memory + code-review-checkpoint |
TDD、代码审查、记忆、构建诊断 |
| 严谨 + 团队 + 记忆 | hackathon-core + cross-session-memory + code-review-checkpoint |
同上 + 架构审查、安全审查 |
| 快速 + 独立 + 无记忆 | hackathon-core |
基础验证、构建诊断 |
| 快速 + 独立 + 记忆 | hackathon-core + cross-session-memory |
基础验证 + 记忆 |
| 平衡 + 任意 + 记忆 | hackathon-core + cross-session-memory + code-review-checkpoint |
规划、验证、代码审查、记忆 |
| 平衡 + 任意 + 无记忆 | hackathon-core + code-review-checkpoint |
规划、验证、代码审查 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 241 lines · 22 tokens per session scan A 51cffabe6c30
setup is a skill published in the GitHub repository znlnzi/claude-config-studio (0 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 2,409 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
specification-writing
Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
golden-rss
Use when testing the rss golden build.
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…
omh-rust
This is a Hermes-native rust workflow skill.