Agent Prompts Warmup
iamtouchskyer/memex
Audit and sync agent instruction files across all coding agent formats.
Initialize this project with the Harness Engineering starter template.
Install Harness Init
$ npx skills add k1ein-chen/Harness-Starter --skill harness-init -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install k1ein-chen/Harness-Starter harness-init --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/harness-init .claude/skills/harness-init && rm -rf skills-srcUse ~/.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/
Install the "harness-init" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-init into .claude/skills/harness-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-init", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-initType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add k1ein-chen/Harness-Starter --skill harness-init -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install k1ein-chen/Harness-Starter harness-init --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/harness-init .agents/skills/harness-init && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "harness-init" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-init into .agents/skills/harness-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-init", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add k1ein-chen/Harness-Starter --skill harness-init -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install k1ein-chen/Harness-Starter harness-init --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/harness-init .cursor/skills/harness-init && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "harness-init" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-init into .cursor/skills/harness-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-init", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/k1ein-chen/Harness-Starter.git --path .claude/skills/harness-init--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add k1ein-chen/Harness-Starter --skill harness-init -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install k1ein-chen/Harness-Starter harness-init --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/harness-init .gemini/skills/harness-init && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "harness-init" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-init into .gemini/skills/harness-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-init", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install k1ein-chen/Harness-Starter harness-initInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add k1ein-chen/Harness-Starter --skill harness-init -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/harness-init .github/skills/harness-init && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "harness-init" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-init into .github/skills/harness-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-init", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add k1ein-chen/Harness-Starter --skill harness-init -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install k1ein-chen/Harness-Starter harness-init --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/harness-init .opencode/skills/harness-init && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "harness-init" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-init into .opencode/skills/harness-init/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-init", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
harness-init- GitHub stars
- 119
- Token cost
- ~995 tokens
- SKILL.md length
- 282 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
Initialize this project with the Harness Engineering starter template.
- Works in 9 steps: ：检查模板文件是否存在 → 检测项目信息 → 填写 CLAUDE.md → …
- The user wants to set up
- SKILL.md covers Step 0：检查模板文件是否存在, Step 1: 检测项目信息, Step 2: 填写 CLAUDE.md and Step 3: Skill 路由发现, plus 5 more sections
- Calls node, git and npm; reaches github.com
What it does
Harness Init is an agent skill from k1ein-chen/Harness-Starter. Initialize this project with the Harness Engineering starter template. Detects project language, installs dependencies, and updates CLAUDE.md placeholders. Use when the user wants to set up or reset the Harness configuration.
Its SKILL.md is about 1000 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Agent instruction files and Project scaffolding. It works with npm. The repository describes itself as: 一套成熟完善的开箱即用的 Claude Code Harness Engineering 模板。三层自动化（安全/感知/审查），集成 LSP、OpenSpec SDD 工作流和 AI 一键初始化。新项目和已有项目均可使用。 The licence is MIT.
When your agent uses it
- The user wants to set up
- Reset the Harness configuration
Example prompts
- “/harness-init”
Requirements
- Python 3
- Node.js
Workflow steps
9 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit c211c43. 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
Shell commands in SKILL.md call:
nodegitnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
github.com
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
Harness Init loads about 995 tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 282 words of instructions outside code blocks.
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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:134
- `pre-tool-check.mjs` — 防止 AI 修改 .env / 高危命令
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 k1ein-chen/Harness-Starter at commit c211c43, republished under its MIT licence (© k1ein-chen). 282 words, ~995 tokens.
Download SKILL.mdSave it as
.claude/skills/harness-init/SKILL.md (or your agent's skills folder).- name
- harness-init
- description
- Initialize this project with the Harness Engineering starter template. Detects project language, installs dependencies, and updates CLAUDE.md placeholders. Use when the user wants to set up or reset the Harness configuration.
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 .agents/hooks/ 和 AGENTS.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/.agents/ .agents/ cp -r /tmp/harness-starter/.claude/ .claude/ cp -r /tmp/harness-starter/docs/ docs/ cp /tmp/harness-starter/AGENTS.md ./ 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 - 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 |
原则：只推荐当前会话中实际可用的 Skill，不要假设用户安装了某个 Skill。
3.3 写入路由表
在 CLAUDE.md 末尾追加一个 # Skill 路由 章节，格式如下：
# Skill 路由
根据项目技术栈和任务类型，推荐以下 Skill：
| 任务类型 | Skill | 触发条件 |
|---------|-------|---------|
| React 组件开发 | vercel-react-best-practices | 涉及 .tsx / .jsx 文件修改 |
| 微信文章排版 | wechat-article-formatter-skill | 用户要求排版/发布公众号内容 |
| Harness 管理 | harness-init / harness-mode | 用户要求调整 Harness 配置 |
| [项目已有] | [skill-name] | [触发场景] |
> Agent 在遇到对应任务时，应优先调用路由表中的 Skill。3.4 询问用户
生成路由表后，向用户确认：
- "我根据你的技术栈（XXX）推荐了这些 Skill 路由，有没有需要增减的？"
- 用户确认后写入 CLAUDE.md
- 如果用户不确定，先写入推荐的，告诉用户随时可以改
Step 4: 检查 Hook 文件
检查 .agents/hooks/ 下核心文件是否存在：
pre-tool-check.mjs— 防止 AI 修改 .env / 高危命令session-context.mjs— 自动注入 git 状态 + 最新交接断点post-tool-check.mjs— （可选）自动格式化pre-compact.mjs— （可选）压缩前保存状态快照
缺失则从模板复制。已有则跳过，不要覆盖。
检查 .claude/settings.json 中是否注册了 Hook（PreToolUse / SessionStart 等）。
缺失则补充，已有的其他配置不要删除。
Step 5: 检查并安装 LSP
检查 typescript-language-server 是否可用。
如果不可用，根据 Step 1 检测到的语言安装对应的 language server。
如果 .lsp.json 里的语言配置和项目不符，根据检测结果修改。
Step 6: 检查 OpenSpec（可选）
询问用户是否需要规范驱动开发工作流。 如果用户确认：
- 安装 CLI：
npm install -g @fission-ai/openspec - 初始化：
openspec init - OpenSpec 会在
.claude/下添加 commands 和 skills，不要阻止
Step 7: 运行健康检查
执行 node scripts/check.mjs，向用户展示结果。
如果有失败项，逐一处理。
可选：向用户介绍 GC 扫描：
node scripts/gc-scan.mjs— 手动执行 8 维度健康扫描- 扫描结果输出或通过 CI 门禁检查
Step 8: 完成提示
向用户说明当前 Harness 状态：
- 已启用的 Hook（PreToolUse / SessionStart）
- 已安装的依赖（LSP / OpenSpec）
- 还需要用户手动做的事（如果有）
© k1ein-chen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/harness-init of k1ein-chen/Harness-Starter.
Open the folder on GitHubat commit c211c43
Compare with similar skills
Harness Init 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Harness Init this skillk1ein-chen/Harness-Starter | 119 | — | ~995 | Automated safety check: Notes | MIT | |
| Agent Prompts Warmupiamtouchskyer/memex | 143 | — | ~1k | Automated safety check: Pass | MIT | |
| Md StarterInfrasity-Labs/dev-gtm-claude-skills | 139 | — | ~2k | Automated safety check: Pass | MIT | |
| Ad HooksCorridorTech/PoseCap | 224 | — | ~2.4k | Automated safety check: Notes | Apache-2.0 | |
| Ad HooksCorridorTech/PoseCap | 224 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| OpenCode Plugin CreatorDevin-AXIS/iPolloWork | 6.8k | 1 repos | ~1.3k | Automated safety check: Pass | Custom licence |
Similar skills
Md Starter
Infrasity-Labs/dev-gtm-claude-skills
Generates a fully structured, project-specific CLAUDE.md by scanning the repo for signal files (package.json, Makefile, .github/workflows/, .env.example, etc.), inferring stack, commands…
Ad Hooks
CorridorTech/PoseCap
Scaffold deterministic quality gates per WORKFLOW.md §11 — pre-commit (lint, format, secret-scan), pre-push (build, unit, integration).
Ad Hooks
CorridorTech/PoseCap
Scaffold deterministic quality gates per WORKFLOW.md §11 — pre-commit (lint, format, secret-scan), pre-push (build, unit, integration).
OpenCode Plugin Creator
Devin-AXIS/iPolloWork
Scaffolds an OpenCode plugin for iPolloWork with the right async factory shape, zod-based tool definitions and hook registration, and explains where to place and register it.
Intent Layer
crafter-station/skills
Set up hierarchical Intent Layer (AGENTS.md files) for codebases.
More from k1ein-chen/Harness-Starter
Harness Start
k1ein-chen/Harness-Starter
Entry point for new users — guides through initialization, architecture review, and cleanup.
Handover
k1ein-chen/Harness-Starter
将当前会话中的技术决策、运维流程或阶段性研发进展，归档为标准工程文档（ADR / SOP / Handover），并自动更新模块内的 README 归档索引。
Harness Mode
k1ein-chen/Harness-Starter
Switch Harness workflow mode (full/hotfix/tweak) and development phase (design/build/fix).
Tech Review
k1ein-chen/Harness-Starter
Reviews technical decisions before implementation. An agent skill from k1ein-chen/Harness-Starter.
Verify Goal
k1ein-chen/Harness-Starter
Independently verifies whether a completed task meets its defined goal conditions.
Harness Gc
k1ein-chen/Harness-Starter
Garbage Collection Agent — 定期扫描项目健康状态，检测文档/代码一致性漂移，自动发起修复提案。
Related
Works with
Categories
Questions about Harness Init
What does Harness Init do?
Initialize this project with the Harness Engineering starter template. Harness Init is an agent skill from k1ein-chen/Harness-Starter. Initialize this project with the Harness Engineering starter template.
When should I use Harness Init?
Harness Init fits situations like: the user wants to set up; reset the Harness configuration.
How do I install Harness Init in Claude Code?
Run `npx skills add k1ein-chen/Harness-Starter --skill harness-init -a claude-code`. Or copy the skill folder (.claude/skills/harness-init in k1ein-chen/Harness-Starter) into .claude/skills/harness-init in your project. Claude Code loads it when a task matches its description.
How do I install Harness Init in Codex?
Run `npx skills add k1ein-chen/Harness-Starter --skill harness-init -a codex`. Or copy the skill folder (.claude/skills/harness-init in k1ein-chen/Harness-Starter) into .agents/skills/harness-init in your project. Codex loads it when a task matches its description.
Can I use Harness Init 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 k1ein-chen/Harness-Starter --skill harness-init -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harness-init, .gemini/skills/harness-init, .github/skills/harness-init and .opencode/skills/harness-init in your project.
What does Harness Init need to run?
Going by SKILL.md and its folder, Harness Init needs the command-line tools its instructions call (node, git and npm). Our summary lists: Python 3; Node.js.
Does Harness Init access the network?
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Harness Init safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Harness Init use?
Harness Init 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 Harness Init use?
About 995 tokens (SKILL.md is roughly 4k 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 Harness Init?
Skills that share tags, products or a category with Harness Init: Agent Prompts Warmup (iamtouchskyer/memex, 143 stars), Md Starter (Infrasity-Labs/dev-gtm-claude-skills, 139 stars), Ad Hooks (CorridorTech/PoseCap, 224 stars) and Ad Hooks (CorridorTech/PoseCap, 224 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Harness Init?
k1ein-chen (a GitHub user) maintains it in k1ein-chen/Harness-Starter, which has 119 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 24, 2026.
Source: k1ein-chen/Harness-Starter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.