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/maxlongint/vibe-coding-rule/agents-mdgit clone --depth 1 https://github.com/maxlongint/Vibe-Coding-RuleWhat 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 | $0.03215 | $0.03215 |
| Opus 5 | $0.01607 | $0.01607 |
| Sonnet 5 | $0.00643 | $0.00643 |
| Haiku 4.5 | $0.00321 | $0.00321 |
Grade A, and why
Vibe-Coding-Rule 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Vibe Coding Rule 版本:v4.2.0
速查:六条底线
- 不伪造成功:真实失败必须显式暴露,不用默认值、空对象、mock、旧链路或跳过检查掩盖。隔离 mock 仅可用于已标明边界的测试或演示,不得冒充真实业务依赖。
- 完成前必须验证:必须说明实际结果;未完成必要验证时不得声称完成或通过,并写明原因、未覆盖项和剩余风险。
- 改行为前先记录:用户明确确认新增或变更需求后,改变外部行为、接口、数据、权限、流程或验收前,必须先更新用户确认的唯一需求载体;未更新前不得实施。
- 不碰敏感信息:不主动读取、打印、提交或传播密钥、凭据、个人敏感信息或未脱敏生产数据;确需处理时须有明确授权并限于最小必要范围。
- 不擅自改变外部状态:未经用户明确要求,不提交、推送、合并、发布、部署、归档需求记录,不删除、覆盖、迁移数据,不写入生产或外部系统,不触发付费、通知或其他难以恢复的操作。
- 拿不准就问:用户已指定的需求承接方向与已确认口径冲突,或用户要求判断承接关系但边界不清时,必须停止实施,说明事实、影响和未知项,并请求用户决定后才能继续。
1. 适用范围与优先级
- 外部指令优先级遵循当前运行环境;本文件不能覆盖平台、法律、权限安全约束或用户本轮明确指令。
- 项目内部冲突按“用户已确认的需求事实 → 当前唯一需求载体 → 适用的项目规范 → 工具输出与运行环境”处理;仍无法判断时停止并询问。
- 用户及已确认记录决定需求事实;源码、测试、版本历史、现有行为和代码分析结果只证明代码事实,不能单独定义需求或验收。
- 多级目录存在多个
AGENTS.md时,优先遵守离目标文件最近且适用的项目规则;无法确定作用域时先确认。 - 修改本规范时,现有条文是审阅对象,不得把它当作阻止修订的前置门禁;敏感信息、权限安全、外部状态和完成前验证约束仍然有效。
2. 内容归属与上下文
AGENTS.md:AI 常驻规则,保存每次 Chat 都必须知道、读取索引前必须生效、用于判断是否读取docs/或是否允许继续的规则;未经用户明确要求不得修改。docs/:长期有效、跨需求适用且按需读取的项目知识,以docs/README.md为索引;新增、调整、移动或删除规范时必须同步维护索引。- OpenSpec change:用户已明确确认的新增需求或需求变更,以及同一需求后续目标、范围、验收、设计、任务、实现记录、验证结果和归档历史。issue、PR、任务卡、设计图与外部文档只作输入来源。
.agents/:随仓库共享的项目级 skill,以.agents/README.md为索引。- Vibe Coding Rule 规范包自带的受管文档若在标题下带有来源标记,接入或升级业务项目时必须保留;业务项目自行新增、生成或沉淀的文档不得使用该标记,以免混淆归属。
- AI 工具或个人环境默认安装的全局能力、内置 skill、Superpowers 目录及其附带文档,不属于本规范依赖、项目规范或受管文件;仅按当前工具实际能力使用,不得复制、迁移或登记为项目文档,除非用户明确要求并确认归属。
- 本规范只维护 OpenSpec + CodeGraph 的完整接入方式,不维护 Lite、单文件复制、可选工具替代或部分接入分支;业务项目接入和升级按
README.md的受管范围整体处理。 - 用户提供的经验、素材、偏好或讨论结论,除非明确要求保存并指定或确认归属,否则不得写入仓库文件或 OpenSpec;归属不明确时先询问。
- 业务项目可在
AGENTS.md维护少量每次 Chat 都必须知道的项目事实,例如技术栈、常用验证命令、源码与测试目录、禁止修改区域;事实必须来自用户确认或项目已有文件,不得猜测补全。 - 项目特有知识通过
docs/README.md索引按需读取;不得为扩大上下文而批量读取。 - 维护
AGENTS.md时优先保持短而稳定;低频、条件化或篇幅较长的知识应放入docs/并通过索引触发,不把一次性经验、临时方案或进行中计划塞入常驻规则。 - OpenSpec 与 CodeGraph 的常驻边界以本文件为准;具体使用方法以工作流教程和当前工具实际形态为准。
3. 需求确认与 OpenSpec
- 普通问答、解释、只读分析、代码理解、仓库状态检查、未确认的需求讨论,以及不改变需求口径的内部整理,默认不使用 OpenSpec。本规范自身的审阅和修订按 §1 的例外处理。
- 新增需求、需求变更或已有需求的继续工作,只能由用户明确指定。AI 不得自行分类、要求确认、查找或启动 OpenSpec;用户未指定时,按其直接授权的任务处理。
- 新增需求或新建关联 change 需要用户确认目标、范围和验收口径,并主动授权创建;需求变更或已有需求后续需要用户明确当前
change-id,或确认只读候选中的承接载体。 - 载体未确认、创建授权未取得、候选关系不清或已确认口径冲突时,不得创建、选定或更新 OpenSpec change,不得形成最终设计、计划、实现或冲突口径。
- AI 对承接关系的判断只作事实说明,不构成选定或创建需求载体的授权。
- 直接授权的小改动若实施中发现会改变外部行为、接口、数据、权限、流程或验收,应先停止并说明影响;用户确认按新增需求或需求变更承接后,再回到 OpenSpec 流程。
- OpenSpec 是规格与变更制品层,承载确认后的需求口径、设计、任务、影响分析、验证结果、未验证项和剩余风险;不根据源码猜需求,不替代用户确认。
- OpenSpec 只在用户明确指定新增需求、需求变更、已有需求后续或归档时作为唯一需求载体使用;需要 OpenSpec 却不可用时,中断依赖该工具的部分并说明阻塞点,不得改用 issue、PR、任务卡或其他载体冒充同等证据。
- 跨 Chat 或上下文压缩后继续已有需求时,用户必须明确当前
change-id,或确认 AI 只读查找后列出的候选;确认前不得自动恢复、选定或修改 change。
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 · 92 lines · 3,215 tokens per session scan A 5036256f0e1f
Vibe-Coding-Rule AGENTS.md is an instructions file published in the GitHub repository maxlongint/Vibe-Coding-Rule (5 stars, last pushed 11d ago), licensed MIT. It adds 3,215 tokens to every session, about $0.0161 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 2026-08-31.
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.
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).
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.