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.
npx agentmods add instructions/233i/agent-skills/agents-mdgit clone --depth 1 https://github.com/233i/agent-skillsWrote 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/instructions/233i/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/233i/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/233i/agent-skills/agents-md.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 | $0.00879 | $0.00879 |
| Opus 5 | $0.00439 | $0.00439 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
agent-skills 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 3d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS 指南
这个文件为在本仓库中工作的 AI 编码代理(Claude Code、Cursor、Copilot、Antigravity 等)提供指引。
仓库概览
这是一个面向资深软件工程师的 Claude.ai / Claude Code skills 集合。Skills 是被打包好的说明和脚本,用来扩展 Claude 以及其他编码代理的能力。
创建一个新技能
目录结构
skills/
{skill-name}/ # kebab-case directory name
SKILL.md # Required: skill definition
scripts/ # Required: executable scripts
{script-name}.sh # Bash scripts (preferred)
{skill-name}.zip # Required: packaged for distribution
命名约定
- Skill 目录:使用
kebab-case,例如web-quality - SKILL.md:必须全大写,文件名必须严格是这个
- Scripts:使用
kebab-case.sh,例如deploy.sh、fetch-logs.sh - Zip 包:文件名必须与目录名完全一致,即
{skill-name}.zip
SKILL.md 格式
---
name: {skill-name}
description: {一句话说明这个 skill 何时使用。应包含类似 "Deploy my app"、"Check logs" 这样的触发短语。}
---
# {Skill Title}
{用简短文字说明这个 skill 的作用。}
## How It Works
{编号列表,解释这个 skill 的工作流程}
## Usage
```bash
bash /mnt/skills/user/{skill-name}/scripts/{script}.sh [args]
Arguments:
arg1- Description (defaults to X)
Examples: {展示 2-3 个常见用法}
Output
{展示用户会看到的输出示例}
Present Results to User
{给 Claude 的呈现模板,说明应该如何把结果展示给用户}
Troubleshooting
{常见问题与解决方式,尤其是网络 / 权限类错误}
### 上下文效率最佳实践
Skills 是按需加载的:启动时只会加载 skill 的名称和描述;只有当代理判断这个 skill 相关时,完整的 `SKILL.md` 才会进入上下文。为了尽量节省上下文:
- **将 `SKILL.md` 控制在 500 行以内**,详细参考资料拆到单独文件
- **描述写得更具体**,让代理更容易判断何时激活这个 skill
- **使用渐进式披露**,把 supporting files 设计成只在需要时才读取
- **优先用脚本,不要把大段代码直接写进文档**,脚本执行本身不消耗上下文,只消耗输出
- **文件引用只适合一层深度**,从 `SKILL.md` 直接链接 supporting files
### 脚本要求
- 使用 `#!/bin/bash` shebang
- 使用 `set -e`,让脚本在出错时快速失败
- 状态信息写到 stderr,例如:`echo "Message" >&2`
- 机器可读输出,例如 JSON,写到 stdout
- 包含临时文件清理的 trap
- 脚本路径应写为 `/mnt/skills/user/{skill-name}/scripts/{script}.sh`
### 创建 ZIP 包
创建或更新一个 skill 后:
```bash
cd skills
zip -r {skill-name}.zip {skill-name}/
给最终用户安装
需要给用户说明这两种安装方式:
Claude Code:
cp -r skills/{skill-name} ~/.claude/skills/
claude.ai:
把 skill 加入项目知识库,或者直接把 SKILL.md 内容粘贴到对话中。
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.
- 3d ago First seen · 111 lines · 879 tokens per session scan A 6088a8a241d5
agent-skills AGENTS.md is an instructions file published in the GitHub repository 233i/agent-skills (6 stars, last pushed 4mo ago), licensed MIT. It adds 879 tokens to every session, about $0.0044 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.