Borrowing it
Nothing to install: this file belongs to yupanzi/kiro2claude. 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/yupanzi/kiro2claude/master/CLAUDE.mdgit clone --depth 1 https://github.com/yupanzi/kiro2claudeWrote 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/yupanzi/kiro2claude/claude-md)<a href="https://agentmods.dev/instructions/yupanzi/kiro2claude/claude-md"><img src="https://agentmods.dev/badge/instructions/yupanzi/kiro2claude/claude-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/yupanzi/kiro2claude/claude-md"><img src="https://agentmods.dev/badge/instructions/yupanzi/kiro2claude/claude-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 | $0.16278 | $0.16278 |
| Opus 5 | $0.08139 | $0.08139 |
| Sonnet 5 | $0.03256 | $0.03256 |
| Haiku 4.5 | $0.01628 | $0.01628 |
Grade A, and why
kiro2claude CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **默认测试模型统一 `claude-opus-5`**:它走原生 reasoning 路径、行为与其它模型不同,统一基准让复现与真实使用一致(curl 设 `model`,Docker 跑 Claude Code 设 `ANTHROPIC_MODEL`,手动脚本读 `_harness.mjs` 的 `CLAUDE_MODEL`)。⚠ 只管**真打上游**的那几层(手动探针 / e2e / CLI harness);单测里的 `cl How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
给在此仓库工作的 Claude Code 看的规范与地图。面向使用者的介绍与 HTTP 路由见 README.md,plugin 指南见 docs/PLUGIN-DEVELOPMENT.md;环境变量、wire format 各有单一真相源——本文件只给指针,不复述。
项目一句话
把 kiro-cli(Kiro 后端)包装成 Claude + OpenAI 双协议代理。Claude 全系 + GPT-5.6(Sol / Terra / Luna);GPT 与 Claude 走完全相同的上游、两个协议端点都可用(踩坑「GPT 完全相同上游」)。MIT:core 管 HTTP 直发 + plugin 加载;两个内置插件(metering 计量、derived credit 反演)默认启用,与第三方插件一样只经 @kiro2claude/plugin-api 契约接入。
运行时:Node ≥ 22 / TypeScript / ES Modules NodeNext / Fastify / pnpm workspace。
Monorepo 边界
packages/ ★ 全部 MIT
├── plugin-api/ 契约包:types + abstract base class,0 runtime deps
├── core/ gateway runtime:HTTP 路由、plugin loader、token manager
├── plugin-metering/ 注入 usage.kiro_metering(credit 计量)
├── plugin-derived/ 反演 Kiro credit → Anthropic token,注入 usage.kiro_derived
└── examples/echo-plugin/ 公开示范 plugin
packages/core/test/manual/ 手工工具(非 CI,vitest 不收;打真实上游会计费)
`kiro-cli-probe.ts` 反向驱动真实 kiro-cli:伪造 event-stream 让它
真的执行某个工具、注入错误码看重试策略、或用
`PROBE_STREAM_SHAPE=text-eof` 看它对无尾帧 EOF 的处理
`_harness.mjs` 下面所有脚本共用:env / 发请求 / 解 SSE / 号段校验 /
**两套协议不变量** / 汇总退出码。新脚本从这里
拿,别再各写一份缩水的不变量集
`protocol-integrity.mjs` 双协议流式完整性:确定性序列 + 协议不变量
`backpressure-integrity.mjs` 慢客户端背压下终结段/内容是否完整
`concurrency-integrity.mjs` 并发下的区间隔离(串扰检测)
`gpt-tool-matrix.mjs` GPT 真实工具往返矩阵:effort × 协议 × 流/非流
(可选图片用例);不重试,失败原样留在报告里
`opus5-effort-matrix.mjs` Opus 5 的 Messages 矩阵:effort × tools/images/
search,报告落 `K2C_REPORT_DIR`
`conversation-fault-server.ts` 会话完整性故障服务器:真实网关转换/传输 + 脚本化
上游,只按历史里的工具回执推进、按场景注入故障
(`text-eof-once` 等);`live-*` 场景经
`_live-conversation-provider.ts` 打真实上游(计费)
`claude-conversation-probe.mjs` / `codex-conversation-probe.mjs`
真实 CLI 三轮持久会话 + Docker 工作区文件任务,
独立验收(`_conversation-workspace.mjs`)
`empty-cli-server.ts` + `claude-empty-probe.mjs` / `codex-empty-probe.mjs`
空响应 9 场景 × 两款真实 CLI(不打上游)
`live-coding-conversation.mjs` / `codex-live-coding-conversation.mjs`
真实模型三轮编码会话(计费;单次预算默认 65 次上游
调用,`K2C_LIVE_MAX_CALLS` 可放宽——opus-5 跑完三阶段
要 ~75+ 次,Codex ~46),验收 oracle 在
`_live-coding-workspace.mjs`;服务器就是
`conversation-fault-server.ts`(`K2C_CONVERSATION_PORT=18943`)
`claude-unicode-input-probe.mjs` 客户端侧 Unicode 转义改写复现(本地假 Anthropic
服务,零上游;结论见 README「已知限制」)
`replay-conversation-history.ts` / `audit-conversation-fixes.mjs`
不调模型:重放录得请求验证历史保留 / 审计探针产物
`codex-subagent-{probe,lifecycle}-server.ts` 见踩坑「Codex code mode」
tools/claude-code/ Claude Code CLI 的 Docker harness(人工点验 + headless 回归,非 runtime)
tools/codex/ Codex CLI 的 Docker harness(Responses 端点点验,非 runtime)
docker/Dockerfile 单一发布镜像(core + 两个内置插件)
.github/workflows/ ci.yml:全 workspace lint+typecheck+test;release.yml:见速查表「发版」
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 · +33 lines · +3,148 tokens per session 1946b02cce9b
- yesterday Changed · +20 lines · +2,780 tokens per session 06a31bab1e7f
- 9d ago First seen · 248 lines · 10,350 tokens per session scan A 9a34196e9276
kiro2claude CLAUDE.md is an instructions file published in the GitHub repository yupanzi/kiro2claude (60 stars, last pushed today), licensed MIT. It adds 16,278 tokens to every session, about $0.0814 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.