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 | $0.13755 | $0.13755 |
| Opus 5.5 | $0.05502 | $0.05502 |
| Sonnet 5.5 | $0.02751 | $0.02751 |
| Haiku 4.5 | $0.01375 | $0.01375 |
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 today.
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 — 858 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。
核心设计理念：前后端一体化。前端 4 套体系（Vue / UniApp / React / HTML）与后端 5 语言矩阵（Java / Python / Go / Node.js / Rust）通过 api-contract.md 契约连接，前端请求层自动适配后端响应信封和错误码，Design Token 命名体系跨框架对齐。
对外定位：本仓库是“古法全栈开发经验 × AI”的公开基础能力层。它提供项目骨架、通用模块、前后端契约、主题与部署规范；不承诺覆盖每个行业业务规则、品牌视觉或个性化产品决策。项目级编排、模板与验收链路由私有仓库 wg-project-kits 持续沉淀。
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） |
| 前后端联调 | 口头约定接口格式、反复沟通 | api-contract.md 契约连接，零沟通成本 |
| 前端样式不统一 | 各页面颜色/间距/字号随意 | Design Token 体系，Vue 与 UniApp 命名完全对齐 |
| 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：
database/下各模块技能（mysql/pgsql/mongodb/redis/kafka/sqlite）提供中间件配置参考。
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-fast-skill/springboot-init-skill - 🐍 一天学会 Python 体系 → 触发
python-fast-skill/fastapi-init-skill - 🐹 一天学会 Go 体系 → 触发
go-gin-init-skill - 🟢 一天学会 Node.js 体系 → 触发
nodejs-init-skill - 🎨 一天学会 Vue 体系 → 触发
vue-base-skill/vue-generate-skill（SPA）/nuxt-generate-skill（SSR） - 📱 一天学会 React 体系 → 触发
react-generate-skill/next-generate-skill - 📱 一天学会 uni-app 体系 → 触发
uniapp-base-skill（基础组件与容器真源）及 14 个独立 uniapp 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.
- today Changed · +1 lines · +29 tokens per session 6cdec0d586e4
- yesterday Changed · +1 lines · +38 tokens per session 0eebf33c0151
- 2d ago Changed · +98 lines · +1,715 tokens per session 771aa761adc8
- 13d ago Changed · +1 lines · +46 tokens per session 91eaf997daef
- 25d ago Changed · +2 lines · +63 tokens per session 5e7720ad83f0
- 29d ago Changed · +2 lines · +120 tokens per session 8b215ecf6450
- 1mo ago Changed · +222 lines · +3,067 tokens per session 7e29fe3a14ac
- 1mo ago Changed · +50 lines · +968 tokens per session 21294ab4896c
- 1mo ago Changed · +3 lines · +112 tokens per session 46b7a1d1eae7
- 1mo ago First seen · 478 lines · 7,597 tokens per session scan A 48fe0027ab22
wg-skills AGENTS.md is an instructions file published in the GitHub repository jiushiwon/wg-skills (121 stars, last pushed yesterday), licensed Apache-2.0. It adds 13,755 tokens to every session, about $0.0550 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.