Borrowing it
Nothing to install: this file belongs to jiushiwon/wg-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.
curl -O https://raw.githubusercontent.com/jiushiwon/wg-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/jiushiwon/wg-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/jiushiwon/wg-skills/agents-md)<a href="https://agentmods.dev/instructions/jiushiwon/wg-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jiushiwon/wg-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.
<a href="https://agentmods.dev/instructions/jiushiwon/wg-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jiushiwon/wg-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.07597 | $0.07597 |
| Opus 5 | $0.03798 | $0.03798 |
| Sonnet 5 | $0.01519 | $0.01519 |
| Haiku 4.5 | $0.00760 | $0.00760 |
Grade A, and why
wg-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 — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wg-skills 仓库规范（Agents Skills 主控文档）
本文件是 wg-skills 仓库的主控规范文档，所有项目级逻辑、结构、流程、规范均沉淀于此。
- Claude 用户：Claude Code 通过
CLAUDE.md间接引用本文件- Codex / Workbuddy / OpenCode / VS Code / Kimi 等其他智能体：直接读取
AGENTS.md- 人类维护者：直接阅读本文
任何对本仓库的修改都必须先更新本文件，再同步到具体 skill 目录与根 README。
一、仓库定位
本仓库是一套 Agents Skills 集合（智能体技能集合），不绑定任何一家厂商、不依赖任何私有协议。
每个子目录对应一个独立 skill（技能），技能通过 SKILL.md 定义触发条件、审查维度与输出格式。任何支持 Skill / Agent 协议的智能体都可以加载并使用本仓库的技能。
1.1 核心理念
将"古法编程"容纳到 AI 体系之中。
AI 时代的编程不是"取代程序员"，而是把传统工程中重复、规范、体系化的部分抽出来，沉淀成可被 AI 调用的技能，让人类专注于业务决策与架构判断。
| 维度 | 古法编程 | 本仓库技能体系 |
|---|---|---|
| 写一个 CRUD 接口 | 查文档、写代码、写测试、写文档（半天） | 一句话触发技能（5 分钟） |
| 搭一套后端骨架 | 选型、写配置、写中间件、写鉴权、写重启脚本（1-2 天） | 触发 xxx-init-skill（10 分钟） |
| 学一门新语言 | 买书、查文档、写 demo（1-2 周） | 触发"一天学会 xxx 体系"技能（半天） |
| 多人协作 | 各自风格、风格不统一 | 技能强制规范（生成即遵守） |
| 项目迭代 | 重构历史债、文档落后 | 技能可平滑升级，文档同步 |
1.2 适用场景
本仓库的技能不是"演示玩具"，而是面向真实的工程项目：
场景 1：具体业务项目
- 🛒 商城系统：商品、订单、支付、库存、优惠券
- 📋 后台管理系统：用户、权限、组织、数据看板、表单工作流
- 📱 App / 小程序：uniapp 一套代码多端发布
- 💬 社区 / 内容平台：帖子、评论、点赞、关注
- 🎓 在线教育：课程、章节、播放进度、考试
场景 2：大型平台项目
需要大量中间件与多插件部署：
- 📨 消息中心：Kafka / Redis Stream / RabbitMQ 接入
- 🔍 搜索引擎：Elasticsearch 集成
- ⚡ 缓存层：Redis Cluster / 多级缓存策略
- 📊 监控告警：Prometheus / Grafana / 链路追踪
- 🔐 统一认证：OAuth2 / SSO / JWT 多端
- 🗄️ 分库分表：ShardingSphere / MyCAT
- 📦 对象存储：MinIO / OSS / S3 兼容
对应技能：
super-deploy-skills/（部署套件，含数据库 / 运行时 / 服务器 / Nginx / Docker / 原生部署 6 大子技能，含 redis / kafka / mongodb / mysql / postgres / go / java / python / nodejs 等中间件安装）。
场景 3：学习各种语言规范
针对小白、追求更高效的 Vibecoding：
- ☕ 一天学会 Java 体系 → 触发
java-backend-skill/springboot-init-skill - 🐍 一天学会 Python 体系 → 触发
python-backend-skill/fastapi-init-skill - 🐹 一天学会 Go 体系 → 触发
go-backend-skill - 🟢 一天学会 Node.js 体系 → 触发
nodejs-backend-skill - 🎨 一天学会 Vue 体系 → 触发
vue-base-skill/vue-generate-skill - 📱 一天学会 uni-app 体系 → 触发
uniapp-base-skill及其 21 个子技能
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 Changed · +103 lines · +1,671 tokens per session 48fe0027ab22
- 5d ago Changed · +2 lines · +46 tokens per session cbdb25e9ee16
- 9d ago First seen · 373 lines · 5,880 tokens per session scan A 3c60e3ccc269
wg-skills AGENTS.md is an instructions file published in the GitHub repository jiushiwon/wg-skills (97 stars, last pushed 2d ago), licensed Apache-2.0. It adds 7,597 tokens to every session, about $0.0380 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.
Other instructions, from other repositories
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.