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/agents-mdgit 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 | $0.01310 | $0.01310 |
| Opus 5 | $0.00655 | $0.00655 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
ai-coding-ok 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 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — ai-coding-ok
⚠️ AI Agent 必读规范(每次任务必须执行)
本项目使用 ai-coding-ok 三层记忆系统。在执行任何任务之前,必须完成以下步骤:
Plan 阶段(强制,任务开始前)
- 读取
AGENTS.md— 本文件,架构速查 - 读取
.github/agent/system-prompt.md— Agent 人格、角色切换、行为边界 - 读取
.github/agent/workflows.md— 场景工作流(Feature/Bug/Refactor/发布) - 读取
.github/agent/coding-standards.md— 编码规范 - 读取
.github/agent/memory/project-memory.md— 项目事实和架构约束 - 读取
.github/agent/memory/decisions-log.md— 历史技术决策 - 读取
.github/agent/memory/task-history.md— 近期任务上下文
Act 阶段(强制,任务结束后)
- 更新
.github/agent/memory/task-history.md— 记录本次任务摘要 - 如有架构决策变化 → 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
⛔ 以上步骤不可跳过。若在使用 superpowers brainstorming / writing-plans, 在调用这些 skill 之前先完成 Plan 阶段,结束后完成 Act 阶段。
项目概述
ai-coding-ok 是一个 AI 编程护栏 Skill 框架。为任意项目安装三层记忆系统(project-memory + decisions-log + task-history)并强制执行 PDCA 工作流,确保 AI Agent 在每次编码任务前后读取和更新项目记忆,解决"AI 修了 bug X 却搞坏了功能 Y"的问题。目标用户是所有使用 Claude Code、GitHub Copilot、Cursor 的开发者。
系统架构与数据流
开发者发起编码任务
│
▼
CLAUDE.md (@AGENTS.md) ──→ AGENTS.md (PDCA 强制指令)
│
├── Plan: 读取 7 个文件(AGENTS + 3 agent 规范 + 3 记忆文件)
├── Do: 编码 + 测试
├── Check: 验证
└── Act: 更新记忆文件(task-history 始终 + decisions-log/project-memory 按需)
跨平台兼容层:
Claude Code → SKILL.md (Mode A/B/C/D) + CLAUDE.md shim
Copilot → .github/copilot-instructions.md (自动加载)
Cursor → .cursor/rules/ai-coding-ok.mdc
Codex → AGENTS.md (自动加载) + .codex/skills/ai-coding-ok/ (skill)
SKILL.md— Skill 定义文件,包含 Mode A(Install) / B(Plan) / C(Act) / D(Upgrade) 完整逻辑templates/zh/— 中文安装模板(AGENTS.md + 三层记忆文件 + agent 规范),安装时自动替换占位符。v4.1.0 起为唯一模板源scripts/— install.sh / install.py 自动化安装脚本 + verify.sh 安装验证 + customize-prompt.md / upgrade-prompt.md 手动触发提示
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 · 88 lines · 1,310 tokens per session scan A e2dbd12cf721
ai-coding-ok AGENTS.md is an instructions file published in the GitHub repository Mark7766/ai-coding-ok (15 stars, last pushed 1mo ago), licensed MIT. It adds 1,310 tokens to every session, about $0.0066 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
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.
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).
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.