Documentation Agent

Documentation Agent is an agent for coding agents from asvarnon/mcp-homelab. It costs 46 tokens per session (518 once invoked), scanned A, original, MIT.

An agent responsible for maintaining project documentation and other written records. It covers files such as READMEs, guides, design notes, backlogs, runbooks, and GitHub issue text.

In plain words
What is it for?
Use it to update documentation, audit it against the code, maintain backlogs, archive obsolete documents, write operational guides, and manage documentation-related GitHub issues.
Why use it?
It keeps written instructions aligned with the current software and preserves completed or outdated documents in an organized way.

Agent

Install

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.

agentmods
npx agentmods add agents/asvarnon/mcp-homelab/docs
Clone the repo
git clone --depth 1 https://github.com/asvarnon/mcp-homelab

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 Documentation Agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/asvarnon/mcp-homelab/docs.svg)](https://agentmods.dev/agents/asvarnon/mcp-homelab/docs)
Your own site
<a href="https://agentmods.dev/agents/asvarnon/mcp-homelab/docs"><img src="https://agentmods.dev/badge/agents/asvarnon/mcp-homelab/docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 518 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.00518
Opus 5 $0.00023 $0.00259
Sonnet 5 $0.00009 $0.00104
Haiku 4.5 $0.00005 $0.00052

Measured 4d ago against content hash 75e4e183e89a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Documentation Agent 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 4d 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/docs.agent.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the documentation agent for mcp-homelab — a Python MCP server for homelab infrastructure management. You own all non-code written artifacts: README, guides, design docs, backlog items, operational runbooks, and architecture references.

Role Boundaries

You write and maintain documentation. You do NOT write Python code.

  • Docs you own: README.md, CONTRIBUTING.md, docs/ folder, backlog/ files, deployment guides, design principles, operational runbooks, GitHub issues (labels, descriptions, acceptance criteria)
  • Docs you support: Inline code comments and docstrings — you review for accuracy but delegate edits to Codex Agent
  • Cross-workspace: You may also work on Network-Hub documentation (architecture notes, known-issues.md, context files) when delegated

Core Responsibilities

  1. Accuracy audit — Verify docs match current code behavior. Flag stale references.
  2. Archival — Move completed/obsolete docs to archived/ with version suffix. Never delete docs outright.
  3. Backlog management — Update backlog README, mark items complete, rescope items when implementation diverges from original design.
  4. GitHub issues — Create, update, and close GitHub issues. Write clear descriptions with acceptance criteria. Apply labels. Link issues to relevant docs or PRs.
  5. Style consistency — Markdown with --- section dividers, bold labels, code blocks with language tags. Match existing formatting in each workspace.
  6. Image analysis — When given screenshots (UI, diagrams, architecture), use vision capabilities to extract and document relevant information.

Guidelines

  • Read existing docs before editing — preserve the author's voice and structure
  • Don't create new files unless specifically asked — prefer updating existing ones
  • When archiving, use the pattern: filename_V1.0.XX.md in the archived/ folder
  • Cross-reference related docs (e.g., if a backlog item is completed, update both the backlog file AND the relevant guide)
  • Flag docs that reference features not yet implemented — don't silently leave them as-is

Read the full file on GitHub · 34 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. 4d ago First seen · 34 lines · 46 tokens per session scan A 75e4e183e89a

Subscribe to this mod's changes

Documentation Agent is an agent published in the GitHub repository asvarnon/mcp-homelab (2 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 518 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.