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/btafoya/boxes-mcp/claude-mdgit clone --depth 1 https://github.com/btafoya/boxes-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/btafoya/boxes-mcp/claude-md)<a href="https://agentmods.dev/instructions/btafoya/boxes-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/btafoya/boxes-mcp/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 | $0.04459 | $0.04459 |
| Opus 5 | $0.02230 | $0.02230 |
| Sonnet 5 | $0.00892 | $0.00892 |
| Haiku 4.5 | $0.00446 | $0.00446 |
Grade C, and why
boxes-mcp CLAUDE.md scanned grade C with 3 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt install -y libvirt-daemon-system qemu-kvm virt-manager Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Add this to your Claude Code config (e.g. `~/.claude/config.json`): Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execFile } from "node:child_process"; How it starts
The opening of the file, as written. The whole thing — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code MCP Server – GNOME Boxes (via libvirt)
A lightweight Model Context Protocol (MCP) server that lets Claude Code manage virtual machines created/managed by GNOME Boxes (which uses libvirt/QEMU under the hood). It exposes safe, task‑oriented tools for listing, starting, stopping, snapshotting, and inspecting VMs.
Works on Ubuntu 22.04/24.04 with libvirt. Requires the user running Claude Code to be in the
libvirt(and oftenkvm) groups.
🗂️ Project Layout
boxes-mcp/
├─ package.json
├─ tsconfig.json
├─ src/
│ ├─ index.ts # MCP server entry – registers tools
│ ├─ exec.ts # thin wrapper for running shell commands safely
│ └─ libvirt.ts # libvirt/virsh helpers & parsers
├─ README.md
└─ systemd/
└─ boxes-mcp.service # optional: run server as a user service
package.json
{
"name": "boxes-mcp",
"version": "0.1.0",
"private": true,
"type": "module",
"description": "Claude Code MCP server for GNOME Boxes (libvirt/virsh)",
"license": "MIT",
"scripts": {
"build": "tsc -p .",
"start": "node dist/src/index.js",
"dev": "node --watch dist/src/index.js",
"compile": "tsc -p ."
},
"dependencies": {
"@modelcontextprotocol/sdk": "^1.2.0"
},
"devDependencies": {
"@types/node": "^22.7.5",
"typescript": "^5.6.3"
}
}
tsconfig.json
{
"compilerOptions": {
"target": "ES2022",
"module": "ES2022",
"moduleResolution": "Bundler",
"outDir": "dist",
"rootDir": ".",
"esModuleInterop": true,
"resolveJsonModule": true,
"strict": true,
"skipLibCheck": true
},
"include": ["src/**/*.ts"]
}
src/exec.ts
import { execFile } from "node:child_process";
import { promisify } from "node:util";
const pexec = promisify(execFile);
export type ExecResult = { stdout: string; stderr: string };
export async function sh(
cmd: string,
args: string[],
opts: { timeoutMs?: number; env?: NodeJS.ProcessEnv } = {}
): Promise<ExecResult> {
const { timeoutMs = 60_000, env = process.env } = opts;
const { stdout, stderr } = await pexec(cmd, args, {
timeout: timeoutMs,
env,
maxBuffer: 10 * 1024 * 1024
});
return { stdout: stdout.toString(), stderr: stderr?.toString() ?? "" };
}
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.
- 3d ago First seen · 529 lines · 4,459 tokens per session scan C 69bcd6cb7afc
boxes-mcp CLAUDE.md is an instructions file published in the GitHub repository btafoya/boxes-mcp (0 stars, last pushed 11mo ago), licensed MIT. It adds 4,459 tokens to every session, about $0.0223 per session on Opus 5. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, 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
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.