Borrowing it
Nothing to install: this file belongs to chenyuxiaojin/cyxj-groksearch. 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/chenyuxiaojin/cyxj-groksearch/main/CLAUDE.mdgit clone --depth 1 https://github.com/chenyuxiaojin/cyxj-groksearchWrote 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/chenyuxiaojin/cyxj-groksearch/claude-md)<a href="https://agentmods.dev/instructions/chenyuxiaojin/cyxj-groksearch/claude-md"><img src="https://agentmods.dev/badge/instructions/chenyuxiaojin/cyxj-groksearch/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/chenyuxiaojin/cyxj-groksearch/claude-md"><img src="https://agentmods.dev/badge/instructions/chenyuxiaojin/cyxj-groksearch/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 | $0.00547 | $0.00547 |
| Opus 5 | $0.00273 | $0.00273 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
cyxj-groksearch 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 8d 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.
What it actually says
CLAUDE.md
联网搜索 MCP Server,注册名 grok-search:Grok(AI 搜索)+ Tavily(抓取/站点映射)+ Firecrawl(截图/降级)。~/CLAUDE.md「证据协议」反复用的就是它。公开仓库 chenhuajinchj/cyxj-groksearch——提交前确认不带密钥或个人信息。
常用命令
uv sync # 装依赖
uv run --extra dev pytest -v # 跑测试
uv run --directory . grok-search # 本地 stdio 调试
./grok-search-launcher.sh # 生产启动(聚合所有 TAVILY_API_KEY* 做多 key 轮询)
结构与坑
- 入口
grok_search.server:main;客户端分层grok_client(OpenAI 兼容 API)/grok_cli_client(本机grokCLI 子进程)/tavily_client/firecrawl_client;key_pool.py多 key 轮询 + cooldown,sources.py信源缓存聚合 - 默认值即协议(2026-08-04 起写进代码):
web_search的extra_sources默认 5(交叉验证,2026-09-02 由 2 调高),默认模型兜底grok-4.3-fast。运行时实际模型以get_config_info为准(~/.config/grok-search/config.json可被switch_model覆盖) - Grok 后端选择(2026-09-02 起):
config.resolve_grok_backend()→cli/api/none。默认auto:有grok命令走 CLI(零 API key,推理强度默认 medium,xhigh 一次两分钟),CLI 挂了回落 API。CLI 输出是 streaming-json,parse_stream_output拼文本 + 收 URL + 剥旁白(工具调用前 <200 字的段) - 防递归红线:grok CLI 会挂载 Claude 的全部 MCP(含本服务),子进程带
GROK_SEARCH_NESTED=1,嵌套实例拒走 CLI。别删这个环境变量 - 改服务端代码后,正在跑的 MCP 会话不会自动生效——需重启 MCP / 重开会话
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.
- 8d ago Changed · +2 lines · +200 tokens per session 149c21c91dd6
- 12d ago First seen · 19 lines · 347 tokens per session scan A 14a82001c8d2
cyxj-groksearch CLAUDE.md is an instructions file published in the GitHub repository chenyuxiaojin/cyxj-groksearch (20 stars, last pushed 9d ago), licensed MIT. It adds 547 tokens to every session, about $0.0027 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).
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.
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).