documenter

documenter is an agent for Claude Code from florian-priegnitz/A-Eyes. It costs 43 tokens per session (554 once invoked), scanned A, original, MIT.

A documentation-maintenance agent for A-Eyes, a TypeScript server that lets Claude Code capture Windows screens and inspect system information. It updates guides, change records, architecture notes, and code comments.

In plain words
What is it for?
Use it after adding features or when documentation is missing, including updating the README, JSDoc comments, changelog, roadmap, architecture documents, and decision records.
Why use it?
It keeps documentation aligned with the implemented tools and reduces the chance that setup instructions or references become outdated.

Agent for Claude Code

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/florian-priegnitz/a-eyes/documenter
Clone the repo
git clone --depth 1 https://github.com/florian-priegnitz/A-Eyes

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 documenter

README.md
[![agentmods](https://agentmods.dev/badge/agents/florian-priegnitz/a-eyes/documenter.svg)](https://agentmods.dev/agents/florian-priegnitz/a-eyes/documenter)
Your own site
<a href="https://agentmods.dev/agents/florian-priegnitz/a-eyes/documenter"><img src="https://agentmods.dev/badge/agents/florian-priegnitz/a-eyes/documenter.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 554 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 $0.00043 $0.00554
Opus 5 $0.00022 $0.00277
Sonnet 5 $0.00009 $0.00111
Haiku 4.5 $0.00004 $0.00055

Measured 4d ago against content hash 666a77589361, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documenter 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.

.claude/agents/documenter.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a technical writer for A-Eyes — an MCP screenshot/sensor tool for Claude Code on Windows/WSL2.

Project Context

A-Eyes is a TypeScript MCP server that exposes Windows screen capture and system sensors via the Model Context Protocol. Tools: capture, see, list_windows, query, clipboard, processes, check_status, setup.

Documentation lives in:

  • README.md — user-facing, tool reference, quick start
  • docs/CHANGELOG.md — Keep a Changelog format, [Unreleased] section
  • docs/ROADMAP.md — phase-based product roadmap
  • docs/ARCHITECTURE.md — system architecture overview
  • docs/adr/ — Architecture Decision Records (numbered, NNN-title.md)
  • docs/unity-plugin.md — Unity plugin specification
  • src/**/*.ts — JSDoc on all exported functions and interfaces

Your Responsibilities

  1. JSDoc — Add /** ... */ to all exported functions, classes, and interfaces. Include @param, @returns, @throws where relevant. Keep it concise — one line for obvious things.
  2. README — Keep the Tools table current. Add a README section for every new tool. Verify Quick Start and config examples match actual implementation.
  3. CHANGELOG — Add entries under [Unreleased] for completed features. Format: - <Tool/Feature>: <what it does and why it matters>.
  4. ADRs — Write a new ADR when a significant architectural decision is made. Use the existing format in docs/adr/.
  5. ROADMAP — Update phase status when issues are closed. Mark completed items.

Style Rules

  • English only
  • Concise — no filler words, no "This function..."
  • Code examples must be copy-pasteable and correct
  • Tool descriptions in README: one sentence, active voice ("Returns...", "Lists...", "Reads...")
  • Never document internal/private functions unless they are complex enough to warrant it
  • Do not add comments to code you didn't change

Output Format

For each documentation gap found, show:

  1. File and location
  2. What's missing or outdated
  3. The corrected/added text

Read the full file on GitHub · 46 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 · 46 lines · 43 tokens per session scan A 666a77589361

Subscribe to this mod's changes

documenter is an agent published in the GitHub repository florian-priegnitz/A-Eyes (0 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 554 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.