Borrowing it
Nothing to install: this file belongs to A1-x-Tech/mcp-google-crux. 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/A1-x-Tech/mcp-google-crux/main/CLAUDE.mdgit clone --depth 1 https://github.com/A1-x-Tech/mcp-google-cruxWrote 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/a1-x-tech/mcp-google-crux/claude-md)<a href="https://agentmods.dev/instructions/a1-x-tech/mcp-google-crux/claude-md"><img src="https://agentmods.dev/badge/instructions/a1-x-tech/mcp-google-crux/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/a1-x-tech/mcp-google-crux/claude-md"><img src="https://agentmods.dev/badge/instructions/a1-x-tech/mcp-google-crux/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 | $0.02003 | $0.02003 |
| Opus 5 | $0.01001 | $0.01001 |
| Sonnet 5 | $0.00401 | $0.00401 |
| Haiku 4.5 | $0.00200 | $0.00200 |
Grade A, and why
mcp-google-crux 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — mcp-google-crux
MCP server for the Chrome UX Report (CrUX) API (TypeScript, stdio). Read-only:
convenience tools compute Core Web Vitals assessments, device breakdowns and p75
trends on top of two raw pass-through tools. The server talks to
chromeuxreport.googleapis.com — exactly two POST-only endpoints
(/v1/records:queryRecord, /v1/records:queryHistoryRecord); auth is a Google
Cloud API key riding as the key= query parameter (no OAuth).
Commands
npm run dev # run from source (tsx watch)
npm test # unit tests + dist smoke, no network
npm run typecheck # types for src + tests
npm run build # emit dist/
npm run smoke # live READ-ONLY call (needs CRUX_API_KEY)
Architecture
src/config.ts— env → config. A missingCRUX_API_KEYis NOT an error: the field staysundefined, the server starts degraded and the client raisesCredentialsError(lives intypes.ts) at call time.ConfigError(with areasoncode) is reserved for malformed values, caught byloadConfigOrDegradedinindex.ts(no such checks exist today). OptionalCRUX_API_BASE,CRUX_TIMEOUT_MS,CRUX_MAX_RETRIES.src/client.ts—queryRecord/queryHistoryRecord→v1/records:*paths: POST only (GET answers a misleading 404), key injected askey=query param,formFactormapped from normalizedphone|desktop|tablettoPHONE|DESKTOP|TABLET, origin XOR url enforced before any fetch.request()first rejects a missingCRUX_API_KEYwithCredentialsError(before the URL is built, the retries and fetch — the message is the product: it names the variable to set and the needed restart), then rejects paths that escape to a foreign origin (SSRF guard), retries 429/5xx/network errors with backoff (honorsRetry-After), enforces an AbortController timeout that also covers reading the body, throwsCruxError(status, body)— andCruxNoDataErrorfor 404, which is a normal "no data" answer.src/cwv.ts— pure CWV logic (no I/O): metric vocabulary, p75 thresholds, ratings, record summarization and trend extraction. All format quirks are handled here.src/tools/vitals.ts—get_core_web_vitals,compare_form_factors(4 requests),compare_origin_vs_url(2 requests),get_cwv_trend.src/tools/records.ts—query_record,query_history_record(raw pass-through).src/tools/util.ts—ok/fail/noDataResult, theREAD_ONLYannotation and shared zod schema factories.src/index.ts— wires everyregister*into the McpServer.loadConfigOrDegradedstarts the server even on a config problem; without a key the initializeinstructionsopen with the unconfigured prefix (setCRUX_API_KEYand restart), plusConfiguration problem: …when aConfigErrorwas caught.src/telemetry.ts— anonymous usage pings (ids/names/versions only, never the key, queried origins/URLs or arguments; fire-and-forget, must never block or throw; opt-outASKADS_TELEMETRY=0).server_startmeans "a usable install started"; an install without a key sendsunconfigured_startinstead. Thereasonis a closed vocabulary (missing_api_key) — never a variable's name or value.startup_failedremains for a config unusable at load time (malformed values), also fire-and-forget.
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 First seen · 115 lines · 2,003 tokens per session scan A e7a7e3caa2d8
mcp-google-crux CLAUDE.md is an instructions file published in the GitHub repository A1-x-Tech/mcp-google-crux (0 stars, last pushed 9d ago), licensed MIT. It adds 2,003 tokens to every session, about $0.0100 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 2026-08-31.
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.