Borrowing it
Nothing to install: this file belongs to steelcutoatmeal/net-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/steelcutoatmeal/net-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/steelcutoatmeal/net-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/steelcutoatmeal/net-mcp/claude-md)<a href="https://agentmods.dev/instructions/steelcutoatmeal/net-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/steelcutoatmeal/net-mcp/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/steelcutoatmeal/net-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/steelcutoatmeal/net-mcp/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 | $0.01036 | $0.01036 |
| Opus 5 | $0.00518 | $0.00518 |
| Sonnet 5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
net-mcp 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `local.py` tools run subprocess commands — always use `subprocess.run()` with list args (never `shell=True`), validate inputs with `_validate_host()`, and return `CommandResult` model How it starts
The opening of the file, as written. The whole thing — 73 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
net-mcp is a FastMCP server (39 tools) that gives LLMs structured access to network engineering data: BGP routing, RPKI/ASPA validation, DNS/DNSSEC, IRR, PeeringDB, IP math, and local diagnostics.
Commands
uv sync # Install dependencies
uv sync --group dev # Install with test dependencies
uv run net-mcp # Run the MCP server
uv run pytest # Run tests (pytest-asyncio, auto mode)
Test tools interactively:
import asyncio
from net_mcp.server import mcp
async def main():
tools = await mcp.list_tools()
result = await mcp.call_tool('tool_name', {'param': 'value'})
print(result.structured_content)
asyncio.run(main())
Architecture
Entry point: src/net_mcp/server.py — creates FastMCP("net-mcp"), calls register_*_tools(mcp) from each tool module, exposes main().
Tool modules (src/net_mcp/tools/): Each module exports one register_<domain>_tools(mcp: FastMCP) function. Inside, tools are defined with @mcp.tool(tags={...}) decorators. Private helper functions are prefixed with _. Seven modules: bgp.py, dns.py, rpki.py, irr.py, peeringdb.py, iptools.py, local.py.
Models (src/net_mcp/models.py): All Pydantic BaseModel classes for tool inputs/outputs. Every tool returns a model. Parameters use Annotated[type, Field(description="...")].
Shared API helpers (src/net_mcp/__init__.py):
ripestat_get(path, params)— addssourceapp=net-mcpto all RIPEstat requestscloudflare_get(path, params)— adds Bearer token, returnsNoneif no token configured (callers must handle graceful fallback)
Config (src/net_mcp/config.py): Singleton via get_config(). Loads from env vars (NET_MCP_*) → config.toml → defaults. Key settings: mrt_cache_dir, cloudflare_api_token, bgproutes_api_key, default_collector, default_dns_resolver, allow_active_local_tools (gates local_nmap/local_curl, off by default).
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 · 73 lines · 1,036 tokens per session scan A fc86fd68f1ce
net-mcp CLAUDE.md is an instructions file published in the GitHub repository steelcutoatmeal/net-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,036 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.