Borrowing it
Nothing to install: this file belongs to K1ta141k/mcp-bench-router. 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/K1ta141k/mcp-bench-router/main/CLAUDE.mdgit clone --depth 1 https://github.com/K1ta141k/mcp-bench-routerWrote 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/k1ta141k/mcp-bench-router/claude-md)<a href="https://agentmods.dev/instructions/k1ta141k/mcp-bench-router/claude-md"><img src="https://agentmods.dev/badge/instructions/k1ta141k/mcp-bench-router/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/k1ta141k/mcp-bench-router/claude-md"><img src="https://agentmods.dev/badge/instructions/k1ta141k/mcp-bench-router/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 | $0.00978 | $0.00978 |
| Opus 5 | $0.00489 | $0.00489 |
| Sonnet 5 | $0.00196 | $0.00196 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
mcp-bench-router 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 10d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-bench-router
MCP server that routes design tasks to designarena.ai's current top-ranked model via OpenRouter.
Architecture
- Transport: stdio (MCP standard)
- 4 MCP tools:
get_best_design_model,get_leaderboard,query_design_model,query_specific_model - 3 services:
leaderboard.ts(designarena.ai API + 2hr cache),openrouter.ts(chat completions + 24hr model list cache),model-mapper.ts(3-tier arena→OpenRouter ID mapping)
Key Files
| File | Purpose |
|---|---|
src/index.ts |
MCP server entry — registers 4 tools, stdio transport |
src/services/model-mapper.ts |
3-tier mapping: static table (100+ entries) → dynamic provider-prefix lookup → fuzzy match |
src/services/leaderboard.ts |
POST /api/leaderboard with {arenaType: "models", category}, sorts by ELO desc, 2hr cache |
src/services/openrouter.ts |
Chat completions + model list fetch, 24hr model list cache |
src/config.ts |
API URLs, cache TTLs, 14 valid categories |
src/types/index.ts |
TypeScript interfaces for all data structures |
src/tools/*.ts |
Individual tool implementations |
Commands
npm run build # tsc → dist/
npm test # vitest run (16 tests across 3 service suites)
npm run dev # tsx src/index.ts (live reload)
npm run test:watch # vitest watch mode
Categories (14)
allcategories, website, gamedev, 3d, dataviz, uicomponent, image, logo, svg, video, imagetoimage, slides, graphicdesign, tts
Each category has a {displayName, description} object in src/config.ts explaining what the benchmark tests (output format, evaluation criteria). Helper functions categoryDisplayName(), categoryDescription(), and buildCategoryParamDescription() surface these in tool schemas and outputs.
Model Mapping Details
The mapper converts designarena.ai model names to OpenRouter IDs:
- Static table — hardcoded for known mismatches (e.g.
claude-sonnet-4-5→anthropic/claude-sonnet-4.5) - Dynamic lookup — tries provider prefixes (
openai/,anthropic/,google/, etc.) against live OpenRouter model list - Fuzzy match — normalizes strings and compares slugs as fallback
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.
- 10d ago First seen · 82 lines · 978 tokens per session scan A 03cfcdfc4318
mcp-bench-router CLAUDE.md is an instructions file published in the GitHub repository K1ta141k/mcp-bench-router (7 stars, last pushed 7mo ago), licensed MIT. It adds 978 tokens to every session, about $0.0049 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).
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.
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.