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 agents/florian-priegnitz/a-eyes/documentergit clone --depth 1 https://github.com/florian-priegnitz/A-EyesWrote 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/agents/florian-priegnitz/a-eyes/documenter)<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>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 | $0.00043 | $0.00554 |
| Opus 5 | $0.00022 | $0.00277 |
| Sonnet 5 | $0.00009 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00055 |
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.
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 startdocs/CHANGELOG.md— Keep a Changelog format,[Unreleased]sectiondocs/ROADMAP.md— phase-based product roadmapdocs/ARCHITECTURE.md— system architecture overviewdocs/adr/— Architecture Decision Records (numbered,NNN-title.md)docs/unity-plugin.md— Unity plugin specificationsrc/**/*.ts— JSDoc on all exported functions and interfaces
Your Responsibilities
- JSDoc — Add
/** ... */to all exported functions, classes, and interfaces. Include@param,@returns,@throwswhere relevant. Keep it concise — one line for obvious things. - README — Keep the Tools table current. Add a README section for every new tool. Verify Quick Start and config examples match actual implementation.
- CHANGELOG — Add entries under
[Unreleased]for completed features. Format:- <Tool/Feature>: <what it does and why it matters>. - ADRs — Write a new ADR when a significant architectural decision is made. Use the existing format in
docs/adr/. - 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:
- File and location
- What's missing or outdated
- The corrected/added text
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.
- 4d ago First seen · 46 lines · 43 tokens per session scan A 666a77589361
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.