Borrowing it
Nothing to install: this file belongs to lizhiyao/oh-my-knowledge. 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/lizhiyao/oh-my-knowledge/main/AGENTS.mdgit clone --depth 1 https://github.com/lizhiyao/oh-my-knowledgeWrote 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/lizhiyao/oh-my-knowledge/agents-md)<a href="https://agentmods.dev/instructions/lizhiyao/oh-my-knowledge/agents-md"><img src="https://agentmods.dev/badge/instructions/lizhiyao/oh-my-knowledge/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/lizhiyao/oh-my-knowledge/agents-md"><img src="https://agentmods.dev/badge/instructions/lizhiyao/oh-my-knowledge/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 | $0.01554 | $0.01554 |
| Opus 5 | $0.00777 | $0.00777 |
| Sonnet 5 | $0.00311 | $0.00311 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
oh-my-knowledge 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - OMK 项目约定
OMK（Observe. Measure. Know.）通过固定模型、改变知识载体，观测和测量 prompt、RAG、skill、agent、workflow 的版本差异。所有改动优先保护测量可比性、证据完整性和用户数据。
本文件是工具中立的项目入场清单。Claude Code 通过 CLAUDE.md import；不为不同工具复制维护第二份项目规则。
开工与交付
- 涉及 commit、PR、分支或发版时，读取 CONTRIBUTING.md 的相关流程；同一任务已读且未变化时复用。
- 修改子目录前，检查从仓库根到目标文件路径上的 AGENTS.md，最近的文件补充或覆盖上层项目约定；普通局部任务不遍历全仓规则。
- 开工先明确需求、非目标、受影响边界和风险。用户确认方向后，在已授权的交付链内连续推进，不在实现、验证、自主 CR 等常规步骤间反复询问下一步。合并和发版分别按已有授权判断，不将合并等同于发布授权。
- 长任务及时更新对应 Issue／PR 的已有执行清单，状态以实际完成情况为准。
- 开发反馈优先跑受影响验证；首次 push 前默认跑一次 yarn ci，除非用户明确要求更窄验证，或改动仅限不影响生成产物、链接、打包与行为的手写文档／规则。首次 push 后事实未变化时，不为交付机械重跑本地门禁；存在远端 CI 时，以其结果补充确认。事实变化时，后续修复成批完成，并按影响范围重跑精准验证或完整门禁，不把远端 CI 当作增量反馈环。
- clean-room 验收只在发布、打包／安装契约变化、真实用户入口变化或风险审查明确要求时执行；触发条件、被测边界与证据未变化时不重复执行。
自主 CR 与完成定义
- 改变行为、契约、打包、文档承诺或仓库规则的改动，在首次 push／交付前自主完成一次 CR；纯机械改动快速复核，深度与风险匹配。
- 首次自主 CR 前必须完整阅读
CODE_REVIEW.md；同一任务规则未变化时复用，不重复加载。以审查者视角只读检查最终变更、直接调用边界、契约和验证证据；发现跨模块影响时沿证据扩大范围。可使用独立 reviewer，否则做 fresh-pass 自审。 - P0～P2 在交付前解决，P3 解决或登记 follow-up。修复后复查受影响面并重跑受影响验证；只有架构／公开行为实质变化、CI 新问题、重要 rebase 冲突或外部审查提出新高风险方向时，才重新做完整 CR。
- Finding 的证据、优先级和格式遵守 CODE_REVIEW.md。无 finding 时明确说明，不制造猜测性问题；门禁、真实用户路径和未验证范围如实报告，不以 CI 绿色代替需求完成。
- 用户要求审查具体 PR 时，将结论直接发布到对应 PR；用户明确要求仅本地审查时不发布，未指定或无法确定对应 PR 时不猜测发布对象。
CR 运行产物隔离
- artifacts/cr/ 和 knowledge/cr/ 不是源码资产，不得在仓库内创建或保留，也不用 .gitignore 隐藏。纯只读审查不创建过程文件；只有实际运行会写盘的 CR 工具时，才用唯一仓库外临时目录保存全部运行产物，并显式配置输出路径，不得执行回写仓库的结果同步。
- CR 前后检查工作树状态，确保审查工具未产生额外污染，不清理或覆盖用户原有修改。Issue／PR／CI 是持久审查记录；只有用户明确要求时才将报告作为项目资产提交。
Code Review Rules
- 不静默改变评分口径、统计语义、prompt 字节、Schema identity 或持久化契约。必要变更显式版本化，在 PR 标题／描述标记对应 BREAKING-*、迁移及测量影响。
- eval-core 保持宿主无关和确定性，不反向依赖 CLI、文件系统、网络、环境变量、具体执行器或 Studio。Core 只表达纯契约与确定性变换，副作用放在 eval-workflows 或对应 adapter。
- 保留来源、时间、关联身份与原始证据；派生视图不覆盖原始证据，观测信号不冒充因果结论。
- 测试使用显式临时根和环境隔离，覆盖失败／中断后的 cleanup 路径；生产写入只落到公开存储契约允许的位置，不擅自写用户目录或全局状态。
- 新建或可安全改名的判别字段使用 eventKind、runtimeKind 等限定名；裸 kind 默认保留给 Artifact.kind。已发布、落盘或对外暴露的 public schema 既有 kind 不顺手改名；必要改名单独迁移并保持旧文件可读。细节见 docs/specs/terminology-spec.md §5.4。
- 用户可见服务 URL 使用 server.start() 返回的实际地址，不硬编码端口。
- .agents/skills/omk/ 是官方 Skill 单一来源，.claude/skills/omk 保持软链，不复制第二份；本文件不重复 Skill 用户教程。
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 · -22 lines · -960 tokens per session 14be1f35cf05
- 2d ago Changed · +42 tokens per session 51afbb11ab99
- 3d ago Changed · +13 lines · +515 tokens per session 17e03788f34d
- 5d ago Changed · -16 lines · -79 tokens per session 1e7dfde5d396
- 9d ago First seen · 79 lines · 2,036 tokens per session scan A 3860a1801cbc
oh-my-knowledge AGENTS.md is an instructions file published in the GitHub repository lizhiyao/oh-my-knowledge (21 stars, last pushed today), licensed MIT. It adds 1,554 tokens to every session, about $0.0078 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).
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.
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.