Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/istarwyh/mcpadvisor/claude-mdgit clone --depth 1 https://github.com/istarwyh/mcpadvisorWrote 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/istarwyh/mcpadvisor/claude-md)<a href="https://agentmods.dev/instructions/istarwyh/mcpadvisor/claude-md"><img src="https://agentmods.dev/badge/instructions/istarwyh/mcpadvisor/claude-md.svg" alt="Measured on agentmods" 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 | $0.04081 | $0.04081 |
| Opus 5 | $0.02041 | $0.02041 |
| Sonnet 5 | $0.00816 | $0.00816 |
| Haiku 4.5 | $0.00408 | $0.00408 |
Grade A, and why
mcpadvisor CLAUDE.md scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await fetch(url); How it starts
The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Instructions for MCPAdvisor
Project Overview
MCPAdvisor is a TypeScript-based CLI tool for discovering and recommending MCP (Model Context Protocol) servers. It helps users find the right MCP server for their needs and provides installation guidance.
Development Commands
Build & Test
pnpm run build- Compile TypeScript and make executablepnpm run test- Run tests with Vitestpnpm run test:watch- Run tests in watch modepnpm run test:coverage- Run tests with coverage reportpnpm run test:jest- Run Jest tests (alternative test runner)pnpm run test:e2e- Run end-to-end tests with Playwrightpnpm run test:meilisearch:e2e- Smart Meilisearch E2E testing (auto-starts services)
Code Quality
pnpm run lint- Run ESLintpnpm run lint:fix- Run ESLint with auto-fixpnpm run format- Format code with Prettierpnpm run format:check- Check code formattingpnpm run check- Run both lint and format check
Dependencies
pnpm run deps:update- Update all dependencies to latestpnpm run deps:check- Check for outdated dependenciespnpm run deps:clean- Clean and reinstall dependencies
Architecture
Core Services
- Search Service (
src/services/searchService.ts) - Main search orchestration - Vector Engines (
src/services/database/) - Vector database implementations- Memory-based vector engine
- Meilisearch integration
- OceanBase integration
- Nacos integration
- Installation Service (
src/services/installation/) - Installation guide generation - Server Service (
src/services/server/) - MCP server management
Search Providers
- Offline Search - Memory-based search with local data
- Meilisearch - Full-text search with vector capabilities
- Nacos - Service discovery integration
- Compass Search - External search provider
Key Directories
src/services/- Core business logicsrc/types/- TypeScript type definitionssrc/utils/- Utility functionssrc/tests/- Test files (Vitest and Jest)docs/- Documentation filesconfig/- Configuration files
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.
- 5d ago First seen · 498 lines · 4,081 tokens per session scan A 43ac11e8f21f
mcpadvisor CLAUDE.md is an instructions file published in the GitHub repository istarwyh/mcpadvisor (89 stars, last pushed 6mo ago), licensed MIT. It adds 4,081 tokens to every session, about $0.0204 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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.
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).