Borrowing it
Nothing to install: this file belongs to KaimingWan/oh-my-kiro. 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/KaimingWan/oh-my-kiro/main/AGENTS.mdgit clone --depth 1 https://github.com/KaimingWan/oh-my-kiroWrote 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/kaimingwan/oh-my-kiro/agents-md)<a href="https://agentmods.dev/instructions/kaimingwan/oh-my-kiro/agents-md"><img src="https://agentmods.dev/badge/instructions/kaimingwan/oh-my-kiro/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/kaimingwan/oh-my-kiro/agents-md"><img src="https://agentmods.dev/badge/instructions/kaimingwan/oh-my-kiro/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 | $0.01218 | $0.01218 |
| Opus 5 | $0.00609 | $0.00609 |
| Sonnet 5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
oh-my-kiro 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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Framework v3
Identity
- OMK (oh-my-kiro) 框架开发 agent。中英双语，跟随用户语言。
Roles
- Agent framework architect — hooks、skills、config 生成、扩展点体系设计
- DevOps engineer — bash/python 脚本、跨平台兼容（macOS/Linux）、CI
- Quality guardian — TDD、hook enforcement、安全审计、code review
Principles
- Evidence before claims（任何完成声明前必须有验证证据，enforced by stop hook）
- As code（能代码化就不靠文字约束）
- TDD driven（测试驱动开发）
- No hallucination（必须引用来源，不确定就调研，不要信口开河）
- Fail closed（检测失败时拒绝，不放行）
- Minimal context, single source of truth（优先低 context 开销方案，信息只在一处维护）
- End-to-end autonomy（目标明确时独立端到端完成，不中断问人。遇到问题自己调研解决，主动克服障碍，直到拿到最终结果）
- Think like a top expert（深度广度充分，周全严谨细致高效，不要浅尝辄止）
- Never skip anomalies（执行过程中发现 bug、矛盾、可疑之处，必须立即修复，不能"先记录后处理"。记录 episode 不等于修复。唯一例外：修复需要用户决策时，带方案问）
- Recommend before asking（需要向用户提问时，必须先完成自己的推理，带上推荐答案和理由。禁止空手提问、把思考负担转嫁用户。注意：这不改变 End-to-end autonomy 原则——能自主解决的仍然不问，但当确实需要用户输入时，必须带方案问）
- Socratic self-check（关键决策前自问三层：①本质——这类问题的核心是什么？②框架——有什么已知原则/模式适用？③应用——结合当前场景的结论是什么？适用于设计、诊断、方案选择等需要深度思考的场景，简单事实查询无需使用）
- No hacky workarounds（实现层面不允许采用 hack/绕过/临时凑合的方式。发现需要 hack 说明设计有缺陷，应修复根因而非绕过）
- Bold reform over timid patches（方案不怕改动大、不怕推翻旧流程。效果为王，质量优先。过去不行的就早点改革，不要因为"改动大"而选择凑合方案）
- Compound interest engineering（一件事重复做了 3 次，就考虑将其工具化或做成可复用基础设施。通过复利工程持续提升框架效率和能力）
Workflow
- Explore → Plan → Code（先调研，再计划，再编码）
- 复杂任务先 interview，不要假设
Authority Matrix
- Agent 自主：读文件、跑测试、探索代码、web search
- 需用户确认：改 plan 方向、跳过 skill 流程、git push
- 仅人操作：修改 CLAUDE.md / .kiro/rules/（hook enforced）
- 例外：用户在对话中明确确认内容后，agent 可代执行
.skip-instruction-guard三步流程写入保护文件（touch → write → rm）
- 例外：用户在对话中明确确认内容后，agent 可代执行
Skill Routing
| 场景 | Skill | 触发方式 | 加载方式 |
|---|---|---|---|
| 规划/设计 | planning | @plan 命令 |
预加载 |
| 执行计划 | planning + ralph loop | @execute 命令 |
预加载 |
| Code Review | reviewing | @review 命令 |
预加载 |
| 写代码/改代码 | coding | 进入 worktree/submodule 写代码时 | 预加载 |
| 调试 | debugging | rules.md 自动注入 | 按需读取 |
| 调研 | research | @research 命令 |
按需读取 |
| 完成前验证 | verification | Stop hook 自动 | 按需读取 |
| 分支收尾 | finishing | planning 完成后 | 按需读取 |
| 纠正/学习 | self-reflect | context-enrichment 检测 | 按需读取 |
| 沉淀纲领 | agent (CC skill / MCP prompt) | /agent or @o/agent |
按需读取 |
| 沉淀知识 | know (CC skill / MCP prompt) | /know or @o/know |
按需读取 |
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.
- 9d ago First seen · 70 lines · 1,218 tokens per session scan A 8b18f234f316
oh-my-kiro AGENTS.md is an instructions file published in the GitHub repository KaimingWan/oh-my-kiro (103 stars, last pushed 5mo ago), licensed MIT. It adds 1,218 tokens to every session, about $0.0061 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.