Borrowing it
Nothing to install: this file belongs to chenklein26-maker/Harness-Starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chenklein26-maker/Harness-Starter/main/.claude/skills/harness-init/SKILL.mdgit clone --depth 1 https://github.com/chenklein26-maker/Harness-StarterWrote 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/chenklein26-maker/harness-starter/harness-init)<a href="https://agentmods.dev/skills/chenklein26-maker/harness-starter/harness-init"><img src="https://agentmods.dev/badge/skills/chenklein26-maker/harness-starter/harness-init.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 5.1 | $0.00044 | $0.01795 |
| Opus 5 | $0.00022 | $0.00898 |
| Sonnet 5 | $0.00009 | $0.00359 |
| Haiku 4.5 | $0.00004 | $0.00179 |
Grade A, and why
harness-init 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 7d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Init
适用三种场景:
- GitHub 安装:用户说"帮我用 Harness Starter 初始化"——还没有模板文件
- 新项目:模板刚复制过来,CLAUDE.md 含占位符
- 已有项目:项目已经开发到一半,想加入 Harness
Step 0:检查模板文件是否存在
检查项目根目录下是否有 .claude/hooks/ 和 CLAUDE.md。
如果不存在(GitHub 安装场景)
用户直接让 AI 安装 Harness Starter,还没有模板文件。需要:
- 从
package.json的repository字段获取仓库地址,克隆到临时目录:git clone https://github.com/<package.json repository>.git /tmp/harness-starter - 复制核心文件到项目:
cp -r /tmp/harness-starter/.claude/ .claude/ cp /tmp/harness-starter/CLAUDE.md ./ cp /tmp/harness-starter/.lsp.json ./ cp /tmp/harness-starter/.gitignore ./.gitignore 2>/dev/null || true cp -r /tmp/harness-starter/scripts/ ./scripts/ 2>/dev/null || true mkdir -p .github/workflows 2>/dev/null cp -r /tmp/harness-starter/.github/ ./.github/ 2>/dev/null || true - 清理临时目录
- 继续执行 Step 1
如果已存在
跳过 Step 0,直接执行 Step 1。
Step 1: 检测项目信息
优先从已有文件自动推断,推断不到再问用户:
检查以下文件,提取项目信息:
package.json→ 项目名、技术栈(React/Vue/Next 等)、测试框架(jest/vitest 等)pyproject.toml→ 项目名、Python 依赖go.mod→ 模块名、Go 版本Cargo.toml→ 项目名、Rust 依赖composer.json→ PHP 项目Gemfile→ Ruby 项目CMakeLists.txt→ C/C++ 项目
对于多语言项目,选择主要技术栈填写。
Step 2: 填写 CLAUDE.md
如果是新项目(含占位符)
用 Step 1 检测到的信息替换 CLAUDE.md 中的 【待填写】 占位符。
如果无法自动推断,询问用户:
- 用途:这个项目是做什么的?
- 技术栈:用什么语言/框架?
- 跑测试:用什么命令?
如果是已有项目(不含占位符)
检查 CLAUDE.md 是否已包含以下核心章节:
- Karpathy 原则(Think Before Coding / 消除信息差 / 讨论与执行分离 / Simplicity First / Surgical Changes / Goal-Driven Execution)
- 全局约定
- 自动审查闭环
如果缺失,补充进去。已有的内容不要覆盖。
Step 3: Skill 路由发现
根据 Step 1 检测到的技术栈,扫描当前可用的 Skill,询问用户最常见的任务类型,生成路由表写入 CLAUDE.md。
3.1 扫描可用 Skill
检查以下位置,汇总所有可用 Skill:
.claude/skills/— 项目本地 Skill(如 harness-init、harness-mode)~/.claude/skills/— 用户全局 Skill- 当前会话中
[Available Skills]列表 - MCP 工具列表(如果有)
3.2 推断任务场景
根据技术栈列出常见任务类型,例如:
| 技术栈 | 常见任务 | 可路由 Skill |
|---|---|---|
| React/Next.js | 组件开发、性能优化 | vercel-react-best-practices |
| 前端/UI | 页面/H5/幻灯片 | frontend-slides |
| Node.js/npm | 包管理、构建 | 项目已有 Skill |
| Python | 测试、格式化 | 项目已有 Skill |
| 公众号/内容 | 微信排版、写作 | wechat-article-formatter |
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.
- 7d ago First seen · 175 lines · 44 tokens per session scan A 1934499bb6f9
harness-init is a skill published in the GitHub repository chenklein26-maker/Harness-Starter (119 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,795 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…