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/igrybkov/mcp-hub/claude-mdgit clone --depth 1 https://github.com/igrybkov/mcp-hubWrote 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/igrybkov/mcp-hub/claude-md)<a href="https://agentmods.dev/instructions/igrybkov/mcp-hub/claude-md"><img src="https://agentmods.dev/badge/instructions/igrybkov/mcp-hub/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 | $0.02269 | $0.02269 |
| Opus 5 | $0.01135 | $0.01135 |
| Sonnet 5 | $0.00454 | $0.00454 |
| Haiku 4.5 | $0.00227 | $0.00227 |
Grade A, and why
mcp-hub 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 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.
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 — 67 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.
What this is
mcp-hub is a meta-MCP server: a single MCP connection that lazily proxies many child MCP servers. The host (Claude Code, Desktop, Cursor) connects only to the hub, which exposes ~8 discovery meta-tools and spawns child servers on first use. Goal: avoid the context bloat (every server's full tool schema injected up front) and process bloat (every server spawned at launch) of wiring servers directly.
Commands
uv sync --dev # install deps (incl. dev group)
uv run pytest # run tests
uv run pytest tests/test_smoke.py::test_imports # single test
uv run ruff check . # lint
uv run ruff format . # format (check-only: --check)
uv run pre-commit install # optional git hooks (ruff lint+format)
uv run mcp-hub list # exercise the CLI against your config
uv run mcp-hub server # run the MCP server (stdio) — what hosts launch
uv run mcp-hub -v server # DEBUG logging to stderr + log file
# Server-management helpers (the "agent workflow" for editing config)
uv run mcp-hub config path # show resolved config sources + the YAML-first write target
uv run mcp-hub add <name> --from-json '<docs snippet>' # scaffold an entry, auto-moving secrets to auth.secrets
uv run mcp-hub validate # lint specs; non-zero exit if a raw secret is in env/headers
uv run mcp-hub skill show # print the bundled "managing MCP servers" guide
uv run mcp-hub skill install # copy the skill into .claude/skills/ (--client cursor for Cursor)
CI (.github/workflows/test.yml) runs ruff check, ruff format --check, and pytest on every push/PR to main. Releases are automated via python-semantic-release driven by Conventional Commits — fix: → patch, feat: → minor, feat!:/BREAKING CHANGE: → major; chore:/docs:/refactor:/test: → no release. The version lives in mcp_hub/__init__.py:__version__ and is bumped by the release bot, not by hand. This package is never published to PyPI (the Private :: Do Not Upload classifier in pyproject.toml is a deliberate guard); distribution is Git + GitHub Releases only.
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 · 67 lines · 2,269 tokens per session scan A 869e59e7e796
mcp-hub CLAUDE.md is an instructions file published in the GitHub repository igrybkov/mcp-hub (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,269 tokens to every session, about $0.0113 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
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).