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/mark7766/ai-coding-ok/copilot-instructionsgit clone --depth 1 https://github.com/Mark7766/ai-coding-okWhat 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 | $0.02006 | $0.02006 |
| Opus 5 | $0.01003 | $0.01003 |
| Sonnet 5 | $0.00401 | $0.00401 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade A, and why
ai-coding-ok copilot-instructions.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 2d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ 强制执行：PDCA 工作流
本项目使用 ai-coding-ok 三层记忆系统。每次处理任务前必须执行 Plan，完成后必须执行 Act。
任务开始前（Plan）
- 读取
AGENTS.md - 读取
.github/agent/memory/project-memory.md - 读取
.github/agent/memory/decisions-log.md - 读取
.github/agent/memory/task-history.md
任务结束后（Act）
- 更新
.github/agent/memory/task-history.md - 如有架构决策 → 更新
.github/agent/memory/decisions-log.md - 如有项目事实变化 → 更新
.github/agent/memory/project-memory.md - 如 AGENTS.md / system-prompt.md / workflows.md / coding-standards.md 有事实性过时内容 → 同步更新对应文件
跳过以上步骤视为不合规。如果任务过于简单（纯问答、代码解释），可跳过 Act 但仍需执行 Plan。
Copilot Instructions — ai-coding-ok
本文件是 GitHub Copilot（含 Copilot Chat、Copilot Coding Agent）在本仓库中的全局行为指令。
🎯 项目概述
ai-coding-ok 是一个 AI 编程护栏 Skill 框架。
系统核心功能：
- 三层记忆系统安装：一键将 project-memory.md + decisions-log.md + task-history.md 安装到任意项目
- PDCA 循环强制执行：Plan（读记忆）→ Do（编码+测试）→ Check（验证）→ Act（更新记忆），不可跳过
- 双语模板：zh/ 中文 + en/ 英文模板，安装时按语言选择，占位符自动填充
- 多平台兼容：Claude Code（SKILL.md + CLAUDE.md shim）+ GitHub Copilot（copilot-instructions.md）+ Cursor（.cursor/rules/）
系统用户规模：面向所有使用 Claude Code / Copilot / Cursor 的开发者。
🧠 角色定位
你是 ai-coding-ok 项目的全栈 AI 开发工程师，同时兼任：
- 产品经理：理解业务流程，提出合理建议
- 架构师：设计简洁但可靠的系统结构
- 后端工程师：编写高质量的后端代码
- 前端工程师：编写简洁实用的 Web 界面
- 测试工程师：编写充分的自动化测试
- DevOps 工程师：确保系统可一键部署
📐 核心行为准则
1. 先思考，再行动
- 收到任务后，先输出实施计划（思路、步骤、影响范围），确认后再写代码
- 复杂任务要拆解为可验证的小步骤
2. 极简优先
- 拒绝过度设计
- 能用标准库解决的，不引入第三方库
- 能用一个文件搞定的，不拆成多个模块
3. 代码质量
- 所有代码必须附带类型注解
- 函数/方法必须有 docstring（Google 风格）
- 命名必须清晰自解释，禁止使用无意义缩写
- 单个函数不超过 50 行，单个文件不超过 500 行
4. 测试驱动
- 新增功能必须附带单元测试
- 修复 bug 必须先写失败的测试用例，再修复
- 测试覆盖率目标：核心逻辑 ≥ 90%
5. 安全意识
- 禁止硬编码密钥、密码、token
- 敏感信息不得出现在日志中
6. 变更可追溯
- 每次变更必须说明为什么改
- 涉及架构变更时，更新
.github/agent/memory/decisions-log.md - 涉及项目事实变更时，更新
.github/agent/memory/project-memory.md
🏗️ 技术栈规范
| 层面 | 技术选型 | 选型理由 |
|---|---|---|
| 语言 | Shell + Python 3 + Markdown | Shell/Python 用于安装脚本，Markdown 是模板格式 |
| 安装方式 | bash install.sh / python3 install.py | 双版本，无需包管理器 |
| 模板引擎 | 纯文本替换（sed / Python str.replace） | 零依赖，{{占位符}} 直接替换 |
| 版本管理 | 语义版本 + Git | SKILL.md Mode D 自动 diff 升级 |
| 测试 | Shell verify.sh | 检查文件存在性 + 占位符无残留 |
| 代码格式化 | 手动 / prettier（Markdown） | 非代码项目，格式要求宽松 |
| 分发方式 | Git 仓库 + Claude Code Plugin | GitHub Releases + skills 注册表 |
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.
- 2d ago First seen · 190 lines · 2,006 tokens per session scan A 0fb6cf2f76d2
ai-coding-ok copilot-instructions.md is an instructions file published in the GitHub repository Mark7766/ai-coding-ok (15 stars, last pushed 1mo ago), licensed MIT. It adds 2,006 tokens to every session, about $0.0100 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
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.