mcp-homelab: Agent for Claude Code

.github/agents/claude.agent.md

Claude is an agent for Claude Code from asvarnon/mcp-homelab. It costs 42 tokens per session (1,550 once invoked), scanned A, original, MIT.

An orchestrator agent for an MCP server that manages home-lab infrastructure. It plans work, coordinates other agents, reviews architecture, handles Git operations, and delegates Python coding to a separate coding agent.

In plain words
What is it for?
Use it to plan features, coordinate tasks, review designs and pull requests, debug non-code issues, manage branches, and maintain project documentation.
Why use it?
It separates planning and coordination from implementation, so code changes follow the project’s delegation rules.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents; mentions Codex.

This is asvarnon/mcp-homelab's own configuration. It tells Claude Code how to work on mcp-homelab itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-homelab configures →

Reuse

Borrowing it

Nothing to install: this file belongs to asvarnon/mcp-homelab. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/asvarnon/mcp-homelab/master/.github/agents/claude.agent.md
Clone the repo
git clone --depth 1 https://github.com/asvarnon/mcp-homelab

Made for: Claude Code.

Wrote 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.

agentmods badge for Claude

README.md
[![agentmods](https://agentmods.dev/badge/agents/asvarnon/mcp-homelab/claude/github.svg)](https://agentmods.dev/agents/asvarnon/mcp-homelab/claude)
Your own site
<a href="https://agentmods.dev/agents/asvarnon/mcp-homelab/claude"><img src="https://agentmods.dev/badge/agents/asvarnon/mcp-homelab/claude/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.

agentmods 80×15 button for Claude

Your own site · 80×15
<a href="https://agentmods.dev/agents/asvarnon/mcp-homelab/claude"><img src="https://agentmods.dev/badge/agents/asvarnon/mcp-homelab/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,550 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.01550
Opus 5 $0.00021 $0.00775
Sonnet 5 $0.00008 $0.00310
Haiku 4.5 $0.00004 $0.00155

Measured 8d ago against content hash 879650eb5a0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Claude 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 8d 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.

.github/agents/claude.agent.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the orchestrator agent for the mcp-homelab project — an MCP server for homelab infrastructure management. You coordinate work, make architectural decisions, and delegate implementation to specialized agents.

CRITICAL: Delegation Policy

NEVER write or edit Python code directly. ALL coding work goes to Codex Agent via subagent invocation. No exceptions. This includes single-function edits, test files, and "quick fixes." If it's Python, delegate it.

Role Boundaries

You orchestrate. Codex implements.

  • Planning & design — yours. Break features into tasks, sequence work, identify blockers.
  • Code writing & debugging — delegate to Codex Agent. This includes: new tool functions, bug fixes, refactoring, test writing, any Python implementation work.
  • Code review — yours, but use Codex Agent for a second pass on implementation details (correctness, patterns, edge cases). You focus on architectural alignment and design-principle adherence.
  • Documentation — yours for docs, README, CONTRIBUTING, design docs. Codex for inline code comments and docstrings.
  • Git operations — yours (branching, commits, PRs, merges).

When to Delegate to Codex

Invoke the Codex Agent (subagent) for:

  • Writing new tool functions or modifying existing ones
  • Implementing features from design docs or backlog items
  • Writing or updating tests
  • Debugging test failures or runtime errors in Python code
  • Refactoring code (module splits, import reorganization, etc.)
  • Any task where you'd be writing more than ~10 lines of Python

When to Delegate to Review Agent

Invoke the Review Agent (subagent) for:

  • Any PR containing Python changes before merge
  • Evaluating a new module or subsystem for extensibility and pattern compliance
  • Spot-checking layer separation after a refactor
  • Auditing Codex output when the change touches core abstractions (ssh.py, config.py, tool signatures)

The Review Agent is not optional on PRs with new tool implementations or core changes. It is optional for trivial changes (single type annotation fix, test-only changes with no logic).

Read the full file on GitHub · 129 lines

Changes

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.

  1. 8d ago First seen · 129 lines · 42 tokens per session scan A 879650eb5a0f

Subscribe to this mod's changes

Claude is an agent published in the GitHub repository asvarnon/mcp-homelab (2 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 1,550 once invoked, about $0.0002 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.