Borrowing it
Nothing to install: this file belongs to aveq-research/surfmeter-mcp. 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/aveq-research/surfmeter-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/aveq-research/surfmeter-mcpWrote 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/aveq-research/surfmeter-mcp/agents-md)<a href="https://agentmods.dev/instructions/aveq-research/surfmeter-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/aveq-research/surfmeter-mcp/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/aveq-research/surfmeter-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/aveq-research/surfmeter-mcp/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 | $0.01105 | $0.01105 |
| Opus 5.5 | $0.00442 | $0.00442 |
| Sonnet 5.5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
surfmeter-mcp 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 2mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
Node.js 20+ and pnpm 10 are required.
pnpm install— install dependenciespnpm check— type check without emittingpnpm test— run all vitest suites; the integration suites skip themselves when credentials are absentpnpm vitest run test/mcp.test.ts— run a single test filepnpm vitest run -t "reports validation errors"— run a single test by namepnpm build— compile tobuild/and markbuild/index.jsexecutablepnpm test:all— type check, test, and build together; run this before committingpnpm format/pnpm format:check— Biome formatting (only the formatter is enabled, there are no lint rules)
The integration tests need a reachable Surfmeter development server and send read-only requests only:
API_ENDPOINT=http://localhost:3001 \
API_KEY=client_admin-replace-me \
pnpm test:integration
Add SURFMETER_FULL_INTEGRATION=1 to also run the extended pass that reads every collection, both search services, settings, and AI status.
Architecture
The server is a thin, layered wrapper around one HTTP API. Requests flow index.ts (stdio bootstrap) → server.ts (McpServer plus the host-facing instructions string) → tools.ts (schemas, safety categories, handlers) → client.ts (HTTP, X-API-KEY, error mapping) → result.ts (wrapping into CallToolResult).
config.ts turns API_ENDPOINT into a complete management endpoint: it appends /client_admin_api/v1 unless the value already ends with it, so both a server origin and a full endpoint work. Handlers therefore pass bare paths such as clients/7.
client.ts handles both plain JSON and Elasticsearch NDJSON scroll responses, and raises SurfmeterApiError carrying the status and the parsed error body. result.ts converts thrown errors into isError tool results instead of protocol errors, so tool failures stay readable to the model.
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.
- 2mo ago First seen · 64 lines · 1,105 tokens per session scan A 978a79d07e49
surfmeter-mcp AGENTS.md is an instructions file published in the GitHub repository aveq-research/surfmeter-mcp (1 stars, last pushed 6d ago), licensed MIT. It adds 1,105 tokens to every session, about $0.0044 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.
surfmeter-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| surfmeter-mcp AGENTS.mdaveq-research/surfmeter-mcp | Instructions file | 1 | 6d ago | MIT | A | 1,105 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| 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 |