Borrowing it
Nothing to install: this file belongs to tanghaojie/Cyber-AI-Forge. 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/tanghaojie/Cyber-AI-Forge/master/AGENTS.mdgit clone --depth 1 https://github.com/tanghaojie/Cyber-AI-ForgeWrote 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/tanghaojie/cyber-ai-forge/agents-md)<a href="https://agentmods.dev/instructions/tanghaojie/cyber-ai-forge/agents-md"><img src="https://agentmods.dev/badge/instructions/tanghaojie/cyber-ai-forge/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/tanghaojie/cyber-ai-forge/agents-md"><img src="https://agentmods.dev/badge/instructions/tanghaojie/cyber-ai-forge/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 | $0.03928 | $0.03928 |
| Opus 5 | $0.01964 | $0.01964 |
| Sonnet 5 | $0.00786 | $0.00786 |
| Haiku 4.5 | $0.00393 | $0.00393 |
Grade A, and why
Cyber-AI-Forge 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 6d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 协作规则
本文件适用于整个仓库。任何 AI Agent 在修改项目时都必须遵守这些规则。
人类修改优先与冲突处理
- 人类维护者写入或确认的代码、配置、测试、文档和明确指令,是判断当前项目意图的首要事实来源。AI 的既有实现、聊天推断、历史设计和归档记录不得覆盖人类修改。
- AI 可以审阅人类修改,但未经人类明确授权,不得以修复、重构、同步、规范化或恢复旧设计为由改写、回退、删除或重命名这些内容。人类明确授权的机械操作(例如仓库格式化)只在授权范围内执行。
- 开始任务时发现的既有未提交改动一律视为人类内容。AI 必须避开这些改动;无法隔离时停止并询问人类,不得自行判断所有权。
- 当实现与测试、现行文档、ADR 或历史记录冲突时,先以人类实现描述当前事实,不得用旧文档反向修改实现。若用户已明确要求同步文档,可以修正含义明确的失配;若发现 bug、风险、行为意图不明或任务范围外的未同步文档,必须说明证据和影响并询问人类下一步,不得静默修复或猜测。
- 人类确认的长期结论必须同步到现行设计或 ADR;AI 协作记录和归档内容不能代替当前规范。
Git 安全门禁与 AI 提交标记
开始修改前的暂存区硬门禁
- 每次 AI 执行任何可能修改代码或仓库文件的任务时,必须在首次修改文件前执行
git diff --cached --quiet,确认当前仓库相对HEAD没有任何已暂存内容。该检查优先于阅读文档和实施任务。 - 如果命令因存在已暂存差异而返回非零状态,AI 必须立即停止,不得修改任何文件,并明确要求人类先提交这些已暂存内容。只有人类完成提交后,AI 重新检查并确认暂存区为空,才能开始工作。
- AI 不得通过代替人类提交既有暂存内容、取消暂存、还原、删除或其他方式绕过门禁。无法确认暂存内容是否属于当前 AI 任务时,一律视为人类既有内容并停止。
- 该门禁检查针对任务开始时的既有暂存内容。AI 完成本轮修改和验证后,可以暂存本轮改动以创建自动提交。
AI 自动提交的强制标记
-
AI 创建的每一个 Git 提交,都必须在提交消息末尾追加以下 trailer,并将模型名称替换为执行该提交的真实 AI 模型名称:
Co-Authored-By: -AI- [AI model name] <[email protected]> -
[AI model name]只是格式占位符,禁止原样写入提交;也不得填写无法确认的简称、产品名或虚构名称。当前执行模型名称不明确时,AI 必须停止提交并说明阻塞。 -
trailer 与提交正文之间必须保留一个空行。即使提交仅包含文档、配置、测试或其他非业务代码改动,也必须保留该标记。
-
创建提交后,AI 必须使用
git log -1 --format=full或等价命令验证 trailer 已正确写入;缺失或错误时不得宣称任务完成。
开始工作前
- 阅读
docs/README.md并判断任务属于foundation、forge或platform。 - 按
docs/README.md的最小阅读协议,只阅读对应作用域中与改动直接相关的design/文档和仍有效的decisions/记录;禁止为建立背景而递归读取整个docs/。 - 检查对应
docs/<scope>/plans/active/中是否已有同一事项的实施计划,避免重复规划。 - 各作用域的
archive/**默认不得读取。只有用户明确要求历史、当前文档明确引用历史证据、排查回归/兼容性或准备恢复旧方案时,才先读对应archive/README.md并选择最相关的一至两份文件。 - 不得仅凭聊天上下文推断长期约定;长期有效的结论必须写入仓库文档。
代码格式
- 仓库根目录
.prettierrc.json是 JavaScript、TypeScript、Vue、JSON、Markdown 和样式文件的 唯一格式来源;AI 生成代码时必须直接遵守该配置,不得从个人编辑器设置推断额外规则。 - 完成代码修改后执行
pnpm format,并在最终验证中执行pnpm format:check。 - pre-commit hook 只负责格式化已暂存文件,不能代替测试、构建或 AI 对最终 diff 的检查。
前端验证边界
apps/frontend不维护单元、组件或端到端自动化测试;前端功能和浏览器行为由人类维护者人工验收。- 除非用户在具体任务中明确要求,AI 不得创建或运行前端自动化测试或浏览器测试。
- AI 可以执行前端格式检查、TypeScript 检查和生产构建,但必须明确这些检查不代替人工功能验收。
- 后端、共享契约和数据库的测试与验证规则不受此前端边界影响。
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.
- 6d ago Changed · +7 lines · +303 tokens per session 53fad9f195b9
- 10d ago First seen · 132 lines · 3,625 tokens per session scan A 56b26e87b07d
Cyber-AI-Forge AGENTS.md is an instructions file published in the GitHub repository tanghaojie/Cyber-AI-Forge (22 stars, last pushed 6d ago), licensed MIT. It adds 3,928 tokens to every session, about $0.0196 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).
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 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.