Harness-Starter: Skill for Claude Code

.claude/skills/harness-start/SKILL.md

harness-start is a skill for Claude Code from chenklein26-maker/Harness-Starter. It costs 42 tokens per session (1,393 once invoked), scanned A, original, MIT.

A guided starting procedure for a project template. It helps new users initialize the project, understand its structure, and remove leftover files or rules that do not fit.

In plain words
What is it for?
Use it when first opening the project, starting a new project, or asking how the template works. It covers initialization, architecture overview, and a review of project rules, files, tools, and goals.
Why use it?
It gives someone opening an unfamiliar project a clear setup path and shared understanding of how the code is organized. It also helps prevent irrelevant template configuration from remaining in the project.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is chenklein26-maker/Harness-Starter's own configuration. It tells Claude Code how to work on Harness-Starter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Harness-Starter configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is [#5] ✔ 健康检查通过 — node scripts/check.mjs → 全绿.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/chenklein26-maker/Harness-Starter/main/.claude/skills/harness-start/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/chenklein26-maker/Harness-Starter

Made for: Claude Code.

Wrote 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.

agentmods badge for harness-start

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenklein26-maker/harness-starter/harness-start.svg)](https://agentmods.dev/skills/chenklein26-maker/harness-starter/harness-start)
Your own site
<a href="https://agentmods.dev/skills/chenklein26-maker/harness-starter/harness-start"><img src="https://agentmods.dev/badge/skills/chenklein26-maker/harness-starter/harness-start.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 133
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.01393
Opus 5 $0.00021 $0.00696
Sonnet 5 $0.00008 $0.00279
Haiku 4.5 $0.00004 $0.00139

Measured 8d ago against content hash b49f706eef93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

harness-start 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 8d 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.

.claude/skills/harness-start/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Start

你是刚打开这个模板的人。无论你手头是空项目还是做到一半的项目,四步走完即可就位。

Step 1:初始化

直接说:

帮我初始化 Harness

AI 会自动执行 harness-init 全流程:检测技术栈 → 填写 CLAUDE.md → 发现 Skill 路由 → 检查 Hook → 安装 LSP → 健康检查。

如果已经在 CLAUDE.md 里填过内容,AI 不会覆盖你写好的部分。

Step 2:整体看一下架构

初始化完成后,说:

帮我梳理一下当前项目架构

AI 会遍历项目文件,输出一份架构概览——目录结构、模块关系、入口文件都在哪里。这一步让你(也让 AI)对项目全貌建立共识,后续改动才有上下文。

Step 3:第一性原理清洗

初始化完成后,AI 已经知道了你的项目是什么。现在基于项目的第一性原理(项目本质、技术栈、核心目标),反向检查 CLAUDE.md 和项目目录里有没有不属于这里的东西

清洗范围

维度 检查什么 示例
🧠 CLAUDE.md 规则 每条规则是否与项目相关? 个人博客不需要 tech-review 引用
📁 项目目录 模板文件是否仍残留? scripts/gc-scan.mjs 对于简单项目可能多余
🛠️ 技术栈对齐 CLAUDE.md 中提到的技术是否项目在用? 纯 Python 项目不应引用 TypeScript
🎯 目标对齐 规则是否服务于项目目标? 博客项目不需要 CI 检查

执行规范

  1. 每条建议必须说明理由,不得只说"删除"不说"为什么"
  2. 必须等用户确认,用户点头才能改
  3. 用户拒绝的要尊重,不能追问"确定吗"
  4. 一轮最多提 5 条,避免轰炸用户

输出格式

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔍 第一性原理清洗
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

根据初始化时获取的信息:
  项目类型:{检测到的项目类型}
  技术栈:{检测到的技术栈}
  核心目标:{用户告知的项目目标}

─────────────────────────────────────
清洗建议(共 N 项):

[1/N] CLAUDE.md · {文件位置}
  现状:{当前内容}
  理由:{为什么不符合项目第一性原理}
  建议:{具体修改操作}
  确认?(y/n) →

[2/N] 项目目录 · {文件/目录路径}
  现状:{当前内容}
  理由:{为什么可以删除或修改}
  建议:{具体操作}
  确认?(y/n) →

...

─────────────────────────────────────
所有建议处理完毕,进入下一步验收。

提醒:CLAUDE.md 的行为准则部分(Karpathy 6 条)是通用原则,对所有项目都有价值,不建议裁剪。重点关注的是"进阶特性"和"具体技术引用"。


Step 4:验收 — 检查是否就位

四步执行完毕时,AI 必须执行以下验收检查并输出结果。不得以"做完了"笼统收尾。

检查项

# 检查项 自动/手动 证据来源
1 CLAUDE.md 无占位符 自动 grep '【待填写】' CLAUDE.md → 0 匹配
2 第一性原理清洗完成 手动确认 Step 3 逐条确认记录完整
3 3 个核心 Hook 已注册 自动 .claude/settings.json 中 PreToolUse/SessionStart/Stop 齐全
4 LSP 可用 自动 检查 language server 安装状态
5 健康检查通过 自动 node scripts/check.mjs 输出全绿
6 项目能正常运行 手动确认 根据项目类型执行对应的 run 命令

验收输出格式

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ 初始化验收报告
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

[#1] ✔ CLAUDE.md 已填写 — 无【待填写】占位符
[#2] ✔ 第一性原理清洗完成 — N 项建议已处理
[#3] ✔ 3 个核心 Hook 已注册 — PreToolUse / SessionStart / Stop
[#4] ✔ LSP 可用 — {language-server}
[#5] ✔ 健康检查通过 — node scripts/check.mjs → 全绿
[#6] ✔ 项目可运行 — {run command} → exit 0

─────────────────────────────────────
结论:全部通过 ✅  项目已就位
─────────────────────────────────────

Read the full file on GitHub · 134 lines

Changes

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.

  1. 8d ago First seen · 134 lines · 42 tokens per session scan A b49f706eef93

Subscribe to this mod's changes

harness-start is a skill published in the GitHub repository chenklein26-maker/Harness-Starter (119 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 1,393 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens