What is skills AGENTS.md?

Repository instructions for creating and checking Claude skills, which are reusable sets of agent guidance and tools.

Use them when adding a skill under `claude-skills/`, writing its `SKILL.md`, adding scripts or reference files, updating the README, and running validation.

They give contributors a consistent folder layout, required metadata, script rules, and validation steps. This reduces missing files and incorrectly formatted skills.

skills AGENTS.md — Instructions file for Codex and OpenCode by ogromwang: Repository instructions for creating and checking Claude skills, w

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.

agentmods

npx agentmods add instructions/ogromwang/skills/agents-md

Clone the repo

git clone --depth 1 https://github.com/ogromwang/skills

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ogromwang/skills/agents-md.svg)](https://agentmods.dev/instructions/ogromwang/skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ogromwang/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/ogromwang/skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 590 This file is loaded in full into every session.

When invoked 590 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00590	$0.00590
Opus 5	$0.00295	$0.00295
Sonnet 5	$0.00118	$0.00118
Haiku 4.5	$0.00059	$0.00059

Measured 3d ago against content hash dea8f670b9eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

AGENTS.md · 108 lines

What it actually says

AGENTS.md

当您需要为本项目添加新的 Claude Skill 时，请遵循以下规范。

项目结构

claude-skills/
├── skill-name/
│   ├── SKILL.md              # 必需：技能定义
│   ├── scripts/              # 可选：执行脚本
│   ├── references/           # 可选：参考资料
│   └── assets/               # 可选：模板资源
└── AGENTS.md                 # 本文件

创建新 Skill 步骤

在 claude-skills/ 下创建目录
创建 SKILL.md，包含 YAML frontmatter 和说明
如需要，在 scripts/ 添加执行脚本
更新 README.md 的 Skills 表格

SKILL.md 格式

必须包含 YAML frontmatter：

---
name: skill-name              # 小写字母+连字符，1-64字符
description: 技能描述...       # 1-1024字符，说明做什么和何时使用
---

建议的正文结构：

# 技能标题

## 使用场景

- 用户可能说的话...
- 触发条件...

## 工作流程

**始终使用脚本执行**：
```bash
bash scripts/script.sh <参数>

详细说明

[Claude 如何执行此任务]

注意事项

[边界情况和错误处理]


## 脚本规范

### 必须使用 `set -e`：

```bash
#!/bin/bash
set -e

使用颜色输出：

RED='\033[0;31m'
GREEN='\033[0;32m'
NC='\033[0m'

info() { echo -e "${GREEN}→${NC} $1"; }
warn() { echo -e "${YELLOW}⚠${NC} $1"; }
error() { echo -e "${RED}✗${NC} $1" >&2; }

必须包含：

-h 或 --help 参数
危险操作的用户确认
清晰的错误信息

参考示例

参考现有 skill 结构：

git-merge - 完整的 SKILL.md + scripts 示例

验证

使用 skills-ref 验证：

skills-ref validate ./skill-name

添加到项目

创建 skill 目录和文件
确保脚本有执行权限：chmod +x scripts/*.sh
更新 README.md 的 Skills 表格
运行验证工具检查

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.

3d ago First seen · 108 lines · 590 tokens per session scan A dea8f670b9eb

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository ogromwang/skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 590 tokens to every session, about $0.0030 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.

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

skills AGENTS.md