agentmods.dev

agent-baton: Instructions file for Claude Code

CLAUDE.md

agent-baton CLAUDE.md is an instructions file for Claude Code from skycitywu/agent-baton. It costs 1,259 tokens per session, scanned A, original, MIT.

A repository-specific instruction document for AgentBaton, a skill whose source code is hosted on GitHub. It explains the repository layout and rules for changing it.

In plain words
What is it for?
It helps agents understand which files control the skill, where templates and guides live, and which constraints to check before editing.
Why use it?
It prevents agents from treating the skill's source repository like a business project or copying its user templates into the wrong place.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is skycitywu/agent-baton's own configuration. It tells Claude Code how to work on agent-baton 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 agent-baton configures →

not rated 3repo 3mo ago A scan 1,259 tokens original MIT
View source ↗ skycitywu/agent-baton
Reuse

Borrowing it

Nothing to install: this file belongs to skycitywu/agent-baton. 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/skycitywu/agent-baton/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/skycitywu/agent-baton

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 agent-baton CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/skycitywu/agent-baton/claude-md.svg)](https://agentmods.dev/instructions/skycitywu/agent-baton/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/skycitywu/agent-baton/claude-md"><img src="https://agentmods.dev/badge/instructions/skycitywu/agent-baton/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,259 This file is loaded in full into every session.
When invoked 1,259 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01259 $0.01259
Opus 5 $0.00629 $0.00629
Sonnet 5 $0.00252 $0.00252
Haiku 4.5 $0.00126 $0.00126

Measured 7d ago against content hash b99c32bfa699, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-baton CLAUDE.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 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.

CLAUDE.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentBaton —— Skill 源码仓库

本文件给 Claude Code 自动读取，让你（AI）理解这个仓库是什么、不该做什么。 不要把这个文件和 assets/templates/CLAUDE.md 混淆——后者是给"使用 AgentBaton 框架的项目"的模板，是本 skill 的产出物。

这是什么仓库

AgentBaton skill 本身的源码，已开源到 https://github.com/skycitywu/agent-baton。

这里不是一个使用 AgentBaton 框架的业务项目。所以：

  • 不要在本仓库内启动 BA / Arch / Dev / TechLead 角色——那些角色是给业务项目用的
  • 不要把 assets/templates/ 的模板拷贝到本仓库根目录——本仓库不是被初始化出来的项目
  • 如果 AgentBaton skill 在本仓库内被错误触发，立即退出，按普通方式回答

仓库结构与各文件用途

路径 角色
SKILL.md Skill 入口，Claude Code 按 frontmatter description 判断触发；改它会改变触发行为
README.md 给 GitHub 访客看的开源介绍（中文）
LICENSE MIT
assets/templates/ 关键资产：用户初始化新项目时被拷贝过去的全套模板，改这里影响所有未来用户
assets/templates/CLAUDE.md 模板 CLAUDE.md（给用户项目用，不是给本仓库用）
assets/templates/config/TEAM_GUIDE.md 协作协议主体（给用户项目用）
assets/templates/config/roles/*.md 4 个角色详细指令（给用户项目用）
assets/templates/docs/ PRD / ARCH / TASKS / INIT_REQ 等文档模板
docs/HUMAN_GUIDE.md 给人类用户读的详细使用指南
CLAUDE.md（本文件） 给 Claude 读，让 AI 理解本仓库性质

关键约束（修改前必读）

SKILL.md 规范

  • 必须 < 500 行（Anthropic Skill 规范，progressive disclosure）
  • frontmatter 必须含 name + description 两个字段
  • description 是 skill 触发的唯一依据，修改后必须双向回归测试：
    • 正向：明确触发场景能起来（"用 AgentBaton 初始化"、"启动 BA 角色"）
    • 反向：日常改代码不会被误触发（"帮我改 main.py 的 bug"）

assets/templates/ 是公共契约

  • 任何修改都会传递给所有未来克隆/更新本 skill 的用户
  • 模板内文件之间的路径引用必须假设：拷贝到用户项目根目录后，相对路径仍然有效（例如 config/roles/BA.md 引用 config/TEAM_GUIDE.md，假设两者都在用户项目的 config/ 下）
  • 不要在模板里写绝对路径或本机路径

本仓库的 commit/push

  • 默认用 global git 身份 skycitywu <[email protected]>
  • 公开仓库，不要把私密讨论、个人邮箱、内网信息 commit 进来
  • push 前用户会确认（已是 Claude Code 默认行为）

测试本地改动

本仓库通过软链注册到 Claude Code 的 skills 目录：

~/.claude/skills/agent-baton -> ~/code/agent-baton

所以改完不需要重新安装，新会话立即生效。验证步骤：

# 1. 全新模式触发测试
mkdir /tmp/baton-test-new && cd /tmp/baton-test-new
claude
# 输入：用 AgentBaton 初始化新项目
# 期望：skill 触发，生成完整目录结构

# 2. 二期接入模式触发测试
mkdir /tmp/baton-test-phase2 && cd /tmp/baton-test-phase2
claude
# 输入：用 AgentBaton 初始化二期接入项目
# 期望：含 docs/phase1/，CLAUDE.md 项目阶段为"二期接入"

# 3. 反向：不应触发
cd ~/code/CyTeamCoding  # 任一非 AgentBaton 项目
claude
# 输入：帮我看下 README 有没有错别字
# 期望：Claude 直接回答，不进入 AgentBaton 流程

Read the full file on GitHub · 104 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. 7d ago First seen · 104 lines · 1,259 tokens per session scan A b99c32bfa699

Subscribe to this mod's changes

agent-baton CLAUDE.md is an instructions file published in the GitHub repository skycitywu/agent-baton (3 stars, last pushed 3mo ago), licensed MIT. It adds 1,259 tokens to every session, about $0.0063 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.

Claude Codeagent-skillsai-codingclaude-skillsframeworkmarkdown
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens