What is skills AGENTS.md?

Repository instructions for learnwy/skills, a collection of reusable instructions that give coding agents repeatable ways to handle tasks. They describe the repository structure and its release and documentation rules.

Understanding the skills repository, creating skills, following its conditional-reflection method, synchronizing shared documents, and running release checks.

They help contributors add or change skills consistently and keep shared documentation synchronized across copies.

How learnwy/skills configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to learnwy/skills. 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/learnwy/skills/main/AGENTS.md

Clone the repo

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

Made for: Claude Code, 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/learnwy/skills/agents-md/github.svg)](https://agentmods.dev/instructions/learnwy/skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/learnwy/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/learnwy/skills/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/learnwy/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/learnwy/skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,968 This file is loaded in full into every session.

When invoked 4,968 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.04968	$0.04968
Opus 5.5	$0.01987	$0.01987
Sonnet 5.5	$0.00994	$0.00994
Haiku 4.5	$0.00497	$0.00497

Measured 2mo ago against content hash 9b56728ad85b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

skills AGENTS.md scanned grade B with 1 finding 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

3. `pnpm run install:hooks` — `scripts/manage-hooks.mjs` 遍历每个包含 `hooks.json` 的技能，运行其 `cli.cjs install --scope global --target both`，在 `~/.claude/settings.json`、`~/.trae/hooks.json`、`~/.trae-cn/hooks.json` 和 `~/.codex/hoo

AGENTS.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

本文件为 AI 代理（Claude Code、Codex、Cursor 等）在本仓库中工作提供指引。

项目概述

个人技能仓库，遵循 Agent Skills Specification 规范，包含可复用的 AI 能力。每个技能是一个独立目录，通过 SKILL.md 文件定义其功能、触发条件和使用模式。

设计哲学：所有 skill 均按"条件反射（Conditional Reflection）"范式组织——明确刺激 → 确定响应。三级反射强度模型、各级最佳实践、强/弱模型适配方案见 .agents/docs/conditional-reflection.md。新增 skill 前请先对照该文档第 7 节的检查表。

该目录下所有 .md 文档为"共享文档"，会通过 pnpm run sync-docs 自动复制到每个 skills/*/references/ 下，确保 skill 单独发布安装后仍可访问。pnpm run release 在 push 前会自动执行同步并由 preflight 检测漂移。只编辑 .agents/docs/ 下的源文件，不要直接编辑 references/ 下带 AUTO-GENERATED 头的副本。

仓库结构

skills/                                    # 仓库根目录
├── AGENTS.md                              # 本文件 — 项目指引
├── CLAUDE.md                              # Claude 专用指引（→ AGENTS.md）
├── LICENSE                                # MIT 许可证
├── agents/                                # 通用方法论代理（权威副本）
│   ├── AGENTS.md
│   ├── problem-definer/
│   ├── story-mapper/
│   ├── domain-modeler/
│   ├── architecture-advisor/
│   ├── responsibility-modeler/
│   ├── spec-by-example/
│   ├── tdd-coach/
│   ├── refactoring-guide/
│   ├── legacy-surgeon/
│   └── test-strategist/
└── skills/                                # 可运行的技能模块
    ├── lwy-knowledge-consolidation/           # 对话洞察持久化（含 Stop 自动 nudge）
    ├── lwy-dispatch/                  # UserPromptSubmit/Stop/SessionStart 单进程调度器
    ├── lwy-status/                    # 跨子系统数据综合视图 + doctor 健康体检
    ├── lwy-llm-wiki/                          # Karpathy 式知识库
    ├── on-contradiction/                  # 矛盾论方法论
    ├── on-practice/                       # 实践论方法论
    ├── on-protracted-war/                 # 论持久战方法论
    ├── lwy-project-agent-writer/              # 创建项目级代理
    ├── lwy-project-skill-installer/           # 将技能安装到项目中
    ├── lwy-project-skill-writer/              # 创建项目级技能
    ├── lwy-requirement-workflow/              # SDD 开发编排器
    ├── lwy-software-methodology-toolkit/      # 10 个方法论代理（兜底）
    ├── lwy-prompt-optimizer/                  # 提示词预检分析与优化
    └── trae-rules-writer/                 # 创建 Trae IDE 规则

Read the full file on GitHub · 322 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.

2mo ago First seen · 322 lines · 4,968 tokens per session scan B 9b56728ad85b

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository learnwy/skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 4,968 tokens to every session, about $0.0199 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

skills AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skills AGENTS.mdlearnwy/skills	Instructions file	5	5mo ago	MIT	B	4,968	Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

skills: Instructions file for Claude Code