Borrowing it
Nothing to install: this file belongs to aleksbuss/mcp-second-opinion. 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/aleksbuss/mcp-second-opinion/main/CLAUDE.mdgit clone --depth 1 https://github.com/aleksbuss/mcp-second-opinionWrote 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/aleksbuss/mcp-second-opinion/claude-md)<a href="https://agentmods.dev/instructions/aleksbuss/mcp-second-opinion/claude-md"><img src="https://agentmods.dev/badge/instructions/aleksbuss/mcp-second-opinion/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/aleksbuss/mcp-second-opinion/claude-md"><img src="https://agentmods.dev/badge/instructions/aleksbuss/mcp-second-opinion/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 | $0.01400 | $0.01400 |
| Opus 5 | $0.00700 | $0.00700 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
mcp-second-opinion 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 9d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-second-opinion — engineering notes
For AI assistants working in this repo
You are working on a small, production-quality MCP server (TypeScript, strict). Keep it small. Match the existing style: pure, fetch/sleep-injectable logic; explicit transient-vs-permanent error handling; a test for every behaviour. Read POST_MORTEMS.md before touching the HTTP client or the fan-out — both entries there are live regressions waiting to happen again.
Stack
TypeScript (strict, NodeNext ESM) · @modelcontextprotocol/sdk (high-level McpServer.registerTool + StdioServerTransport) · zod pinned to v3 (the SDK is built against it — see PM #2) · Vitest · GitHub Actions CI (Node 18, 20 & 22 — the matrix matches the engines claim).
Architecture — one job per file
src/openrouter.ts HTTP client: chat (retries, error taxonomy, usage) + embeddings
src/panel.ts Fan-out (bounded concurrency + dedup) + synthesis + Markdown render
src/disagreement.ts Embedding-distance scoring (cosine, pairwise) — embedder injected
src/embedder.ts Adapts openrouter.embed() to the Embedder interface
src/config.ts Pure config parsing: model lists, caps, env coercion
src/handler.ts The second_opinion flow (key check → fan-out → score → synth → compose), fetch + embedder injected so the glue is unit-tested
src/index.ts MCP server: tool registration, arg schemas, env → config, stdio (the only file that reads process.env / the global fetch)
The request flow: index.ts (tool call, env → config) → handler.runSecondOpinion → config (normalise models) → panel.askPanel (fan out, bounded) → openrouter.chatCompletion (per model, retried) → best-effort disagreement.scoreDisagreement → optional panel.synthesize → panel.composeResult (Markdown + isError back to the client). The handler takes fetch/sleep/embedder as injected deps, so the whole flow is tested without a network in handler.test.ts.
Contracts (don't break these)
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.
- 9d ago First seen · 52 lines · 1,400 tokens per session scan A 1c713d8dc540
mcp-second-opinion CLAUDE.md is an instructions file published in the GitHub repository aleksbuss/mcp-second-opinion (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,400 tokens to every session, about $0.0070 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.