Borrowing it
Nothing to install: this file belongs to cfrs2005/awesome-claude-code-relay. 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/cfrs2005/awesome-claude-code-relay/main/CLAUDE.mdgit clone --depth 1 https://github.com/cfrs2005/awesome-claude-code-relayWrote 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/cfrs2005/awesome-claude-code-relay/claude-md)<a href="https://agentmods.dev/instructions/cfrs2005/awesome-claude-code-relay/claude-md"><img src="https://agentmods.dev/badge/instructions/cfrs2005/awesome-claude-code-relay/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/cfrs2005/awesome-claude-code-relay/claude-md"><img src="https://agentmods.dev/badge/instructions/cfrs2005/awesome-claude-code-relay/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 | $0.01914 | $0.01914 |
| Opus 5.5 | $0.00766 | $0.00766 |
| Sonnet 5.5 | $0.00383 | $0.00383 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
awesome-claude-code-relay CLAUDE.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 3d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
本仓库是 Claude Code / Claude API 中转站的中立社区目录 + 自动化基础验证平台（MQ / ModelQuality）。
定位（给在此仓库工作的 AI 助手）
- 无 AFF：任何链接（website / api_base / notes）不得包含 aff、invite、ref、ic、code 等推广或返利参数。历史版本曾带推广参数，2026-11 已全部清除；发现新增推广参数必须在审查中标为一票否决。
- 收录 ≠ 推荐，验证通过 ≠ 安全：禁止星级、排名、"稳定好用"式推荐话术。
models_claimed是服务商声称，不是事实。 - 目录数据是结构化的：
providers/<id>.json（schema：providers/schema.json）。README 的目录表由scripts/build_readme.py生成，不要手改标记区内的表格。
关键文件
| 路径 | 作用 |
|---|---|
providers/*.json |
服务商条目（每个服务商一个文件，id 与文件名一致；一个 PR 只能新增一个） |
providers/schema.json |
条目 JSON Schema（自动校验依据） |
mq/mq.py |
MQ 检测引擎：模型目录 / 端点可用性 / 协议兼容性 / 身份证据（含签名回验）/ 稳定性 |
scripts/check_mq_report.py |
核验 PR 里贴的 MQ 报告（存在性、端点一致性、时效、结论） |
scripts/pr_guide.py |
生成 PR 指引评论（告诉提交者怎么跑、怎么贴） |
scripts/check_providers.py |
PR 确定性校验（自动合并的依据之一） |
scripts/update_verification.py |
合并后把报告结论回写到条目 verification 字段 |
scripts/build_readme.py |
从 providers/*.json 生成 README 目录表 |
.github/workflows/providers-check.yml |
PR 校验 + Watch 检查 + MQ 报告门禁 + 自动合并 |
.github/workflows/mq-guide.yml |
PR 打开时发布「怎么跑 MQ、怎么贴报告」指引 |
.github/workflows/claudecode.yml |
GLM 驱动的 Claude Code（@claude 交互 + PR 分诊 + 报告解读） |
mq/hub/ |
可选：报告托管与浏览服务，不参与合并门禁 |
docs/verification-design.md |
验证流程、威胁模型（公开透明文档） |
docs/README.md |
docs 索引；新增文档按 YYYY-MM-DD-<english-kebab>.md 命名并登记 |
收录验证的形态（NQ 式，勿改回服务端代跑）
对照 VPS 圈的 NodeQuality：测量在用户自己的机器上发生，平台只做核验和呈现。
- 提交者本地跑
mq/mq.py，把报告全文贴进 PR。我们不接收、不转发、不存储任何 Key。 - 报告第一行是
<!--MQ-REPORT:<base64>-->机器可读块，由引擎生成，用户整份复制。 它是结构化输入，不是防伪凭证——报告仍是可读可改的 markdown，信任来自端点一致性与社区监督。 - 门禁只做四件确定性的事：报告存在、host 一致、未过期（30 天）、结论合格。 不做人工主观评审，也不用大模型判定放行。
- 大模型（GLM）只负责解读报告写人话，永远不参与放行判定。
不要把流程改回「提交绑定码 → 上传临时 Key → 服务端跑测试」。那会重新引入 密钥托管风险和审核式产品形态，两件事都不是本项目要的。
报告由提交者在本地生成并贴进 PR。仓库侧只解析报告首行的 <!--MQ-REPORT:...--> 机器可读块，不代跑、不接收 Key。历史 PR 可能仍指向旧的 Hub 工作台地址 https://mq.80aj.com/pr/<PR号>（mq/hub/ 保留为可选服务，不在关键路径上）。
运维细节不写入仓库。凭证只通过受控的运行环境和 CI Secret 提供，绝不进入代码、文档、评论或报告。
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.
- 3d ago Changed · +50 lines · +1,622 tokens per session 96cd97be5701
- 2mo ago First seen · 44 lines · 292 tokens per session scan A 8b4240c8aa20
awesome-claude-code-relay CLAUDE.md is an instructions file published in the GitHub repository cfrs2005/awesome-claude-code-relay (5 stars, last pushed 2d ago), licensed MIT. It adds 1,914 tokens to every session, about $0.0077 per session on Opus 5.5. 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.
awesome-claude-code-relay CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| awesome-claude-code-relay CLAUDE.mdcfrs2005/awesome-claude-code-relay | Instructions file | 5 | 2d ago | MIT | A | 1,914 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |