harness-step1-create-agents-md

harness-step1-create-agents-md is a skill for Claude Code, Codex from simbajigege/book2skills. It costs 153 tokens per session (2,375 once invoked), scanned A, original, MIT.

A project-documentation setup for coding agents. It scans a repository and creates an AGENTS.md guide plus a docs/ knowledge base describing the project's purpose, architecture, conventions, technology, and business context.

In plain words
What is it for?
Use it when adding agent support, starting harness engineering, creating AGENTS.md, organising project documentation, or documenting the business problem and technical structure.
Why use it?
It puts important project knowledge into files that an agent can read, instead of leaving that knowledge only in people's heads or scattered across conversations. This helps agents make decisions that fit the existing project.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions AGENTS.md.

Good fit Use it when adding agent support, starting harness engineering, creating AGENTS.md, organising project documentation, or documenting the business problem and technical structure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/simbajigege/book2skills/harness-step1-create-agent-md
Install

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.

Any agent
npx skills add simbajigege/book2skills --skill harness-step1-create-agent-md
Clone the repo
git clone --depth 1 https://github.com/simbajigege/book2skills

Made for: Claude Code, Codex.

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-step1-create-agents-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/simbajigege/book2skills/harness-step1-create-agent-md/github.svg)](https://agentmods.dev/skills/simbajigege/book2skills/harness-step1-create-agent-md)
Your own site
<a href="https://agentmods.dev/skills/simbajigege/book2skills/harness-step1-create-agent-md"><img src="https://agentmods.dev/badge/skills/simbajigege/book2skills/harness-step1-create-agent-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for harness-step1-create-agents-md

Your own site · 80×15
<a href="https://agentmods.dev/skills/simbajigege/book2skills/harness-step1-create-agent-md"><img src="https://agentmods.dev/badge/skills/simbajigege/book2skills/harness-step1-create-agent-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,375 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 pass 7 Sept 2026
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 $0.00153 $0.02375
Opus 5 $0.00077 $0.01188
Sonnet 5 $0.00031 $0.00475
Haiku 4.5 $0.00015 $0.00237

Measured 12d ago against content hash 625203e5f82a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

harness-step1-create-agents-md 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 12d 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.

skills/harness-step1-create-agent-md/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Step 1: 创建 AGENTS.md 与 docs/ 知识库

目标

为项目建立 agent 可读的知识库地基:

  • 一份简短的 AGENTS.md(~100 行,作为"目录"而非百科全书)
  • 一套 docs/ 目录结构,存放真正的知识

核心原则:agent 看不到的东西就不存在。项目的业务定位、目标用户、解决的问题、架构决策、命名约定和技术选型,必须以文件形式存在于仓库中。


执行步骤

Step 1:扫描项目

按顺序收集项目信息,已知信息跳过,不要重复提问

# 1. 项目根目录结构(2层)
find . -maxdepth 2 -not -path '*/node_modules/*' -not -path '*/.git/*' \
  -not -path '*/__pycache__/*' -not -path '*/dist/*' -not -path '*/.next/*' | sort

# 2. 识别技术栈
cat package.json 2>/dev/null || cat pyproject.toml 2>/dev/null || \
  cat go.mod 2>/dev/null || cat Cargo.toml 2>/dev/null || echo "未找到包管理文件"

# 3. 查看是否已有文档
ls -la *.md 2>/dev/null; ls -la docs/ 2>/dev/null

# 4. 查看 README(如有)
head -80 README.md 2>/dev/null || head -80 readme.md 2>/dev/null

从扫描结果中提取:

  • 项目名称和用途(从 README 或 package.json)
  • 业务定位和用户价值(服务谁、解决什么问题、提供哪些可见能力)
  • 典型业务场景(从 README 功能、示例、截图说明和已有产品文档提取)
  • 技术栈(语言、框架、主要依赖)
  • 目录结构(主要模块划分)
  • 已有文档(避免重复,复用现有内容)

业务内容必须区分“仓库明确声明的现有能力”和“根据功能推断的潜在场景”。仅有营销描述、没有代码或产品文档证据的内容标注「待 Step 2 验证」。

Step 2:生成 docs/ 目录结构

创建以下文件(内容根据扫描结果填写,不要留空占位符):

必须创建的文件:

AGENTS.md                    ← 目录文件,~100行
docs/
├── business-solution.md     ← 业务定位、用户问题、解决方案和能力边界
├── ARCHITECTURE.md          ← 模块划分、依赖关系
├── CONVENTIONS.md           ← 命名规则、代码风格
├── TECH_DECISIONS.md        ← 技术选型理由
├── QUALITY.md               ← 验收标准、完成定义
└── exec-plans/
    ├── active/              ← 当前进行中的计划(空目录,放 .gitkeep)
    ├── completed/           ← 已完成的计划(空目录,放 .gitkeep)
    ├── backlog.md           ← 待开发功能列表(已知需求,尚未排期)
    └── tech-debt-tracker.md ← 已知技术债务

可选创建(根据项目实际情况判断):

docs/
├── design-docs/             ← 有复杂设计决策时创建
├── product-specs/           ← 有产品规格时创建
└── references/              ← 有外部文档需要本地化时创建

Step 3:写 AGENTS.md

严格遵守以下格式,控制在 100 行以内:

# [项目名称] — Agent 工作指南

## 这是什么项目
[1-3句话:项目用途、核心功能、服务对象]

## 快速定向
- **我在哪个目录?** 运行 `pwd` 确认工作目录
- **技术栈**:[语言] + [框架] + [主要工具]
- **入口文件**:[主要入口,如 src/main.ts、app/main.py]
- **启动命令**:[如何启动开发服务器]
- **测试命令**:[如何跑测试]

## 知识库地图
在做任何修改前,先阅读相关文档:

| 我想了解... | 去读这个文件 |
|------------|-------------|
| 业务定位、目标用户、解决什么问题 | `docs/business-solution.md` |
| 整体架构、模块划分 | `docs/ARCHITECTURE.md` |
| 命名规则、代码风格 | `docs/CONVENTIONS.md` |
| 技术选型原因 | `docs/TECH_DECISIONS.md` |
| 什么叫"完成" | `docs/QUALITY.md` |
| 当前进行中的计划 | `docs/exec-plans/active/` |
| 待开发功能列表 | `docs/exec-plans/backlog.md` |
| 已知技术债务 | `docs/exec-plans/tech-debt-tracker.md` |

## 工作规范
1. **改之前先读**:修改任何模块前,先读对应的架构文档
2. **完成即提交**:每个功能完成后立即 git commit,写清楚做了什么
3. **更新文档**:如果你的修改影响了架构或约定,同步更新 docs/
4. **不要猜**:看不懂的地方先读文档,文档没有再问

## 禁止事项
[根据项目实际情况填写,例如:]
- 不要直接修改 `generated/` 目录下的文件(自动生成)
- 不要跳过测试直接合并
- 不要在 service 层引用 UI 组件(见 docs/ARCHITECTURE.md)

Read the full file on GitHub · 207 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 207 lines · 153 tokens per session scan A 625203e5f82a

Subscribe to this mod's changes

harness-step1-create-agents-md is a skill published in the GitHub repository simbajigege/book2skills (163 stars, last pushed 17d ago), licensed MIT. It adds 153 tokens to every session and 2,375 once invoked, about $0.0008 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

marketing-strategy-pmm

Product marketing, positioning, GTM strategy, and competitive intelligence. Includes ICP definition, April Dunford positioning methodology, launch playbooks, competitive battlecards, and international market entry guides. Use when developing positioning, planning product launches, creating messaging, analyzing…

davila7/claude-code-templates · 92 tokens

loki-mode

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention.…

davila7/claude-code-templates · 152 tokens

email-sequence

When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle…

davila7/claude-code-templates · 84 tokens

qa-test-planner

Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.

davila7/claude-code-templates · 34 tokens

gepetto

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

davila7/claude-code-templates · 35 tokens

pydantic-ai

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

davila7/claude-code-templates · 32 tokens