eagleeye

eagleeye is a skill for Claude Code, Codex from baimaomaomao556/eagleeye-mcp. It costs 117 tokens per session (1,218 once invoked), scanned A, a copy of eagleeye, MIT.

A visual inspection toolbox that works through EagleEye MCP, a connection for using its visual tools. It can inspect live screens or windows and measure pixels, text, templates, and visual changes.

In plain words
What is it for?
Use it for screenshots, OCR, waiting for interfaces, UI checks, visual regression, and pixel-level comparisons.
Why use it?
It helps verify what a screen or application actually looks like, including changes between versions. It requires EagleEye to be connected to the agent host.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for screenshots, OCR, waiting for interfaces, UI checks, visual regression, and pixel-level comparisons.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/baimaomaomao556/eagleeye-mcp/eagleeye
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.

Any agent
npx skills add baimaomaomao556/eagleeye-mcp --skill eagleeye
Clone the repo
git clone --depth 1 https://github.com/baimaomaomao556/eagleeye-mcp

Made for: Claude Code, Codex.

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 eagleeye

README.md
[![agentmods](https://agentmods.dev/badge/skills/baimaomaomao556/eagleeye-mcp/eagleeye/github.svg)](https://agentmods.dev/skills/baimaomaomao556/eagleeye-mcp/eagleeye)
Your own site
<a href="https://agentmods.dev/skills/baimaomaomao556/eagleeye-mcp/eagleeye"><img src="https://agentmods.dev/badge/skills/baimaomaomao556/eagleeye-mcp/eagleeye/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 eagleeye

Your own site · 80×15
<a href="https://agentmods.dev/skills/baimaomaomao556/eagleeye-mcp/eagleeye"><img src="https://agentmods.dev/badge/skills/baimaomaomao556/eagleeye-mcp/eagleeye.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,218 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 86% copy Near-identical to another mod 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 $0.00117 $0.01218
Opus 5 $0.00059 $0.00609
Sonnet 5 $0.00023 $0.00244
Haiku 4.5 $0.00012 $0.00122

Measured 10d ago against content hash 4af7b4c4f88b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

eagleeye 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 10d 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.

Origin

This is a copy

86% identical to eagleeye — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/eagleeye/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EagleEye — DSH / Agent Skills 薄包装

这不是第二个 glance/ground CLI。能力在 MCP 工具 eagleeye_* 上。 本文件只规定:何时用、何时不用、先调哪一层。

仓库计划账号:baimaomaomao556。发布后安装 skill:

npx skills add baimaomaomao556/eagleeye-mcp --skill eagleeye

仍须在 Host 里接入 MCP Server(见仓库 docs/HOSTS.md);本 skill 不替代 stdio 进程。

先看工具列表

  • 对话里已经出现 eagleeye_capture_screen 等工具 → 直接调用,不要自己写 Pillow/Tesseract,也不要改去跑 modlens/vision-tools 的脚本。
  • 没有这些工具 → 停下来告诉用户:需要按仓库 docs/HOSTS.md 把 EagleEye 以 stdio MCP 接入当前 Host。不要假装已经截到了屏。

不要用 EagleEye 的时候

  • 已经能看见用户贴的图(原生多模态)→ 自己看,不要再截屏。
  • 任务只是「读这张已有图片里的字/布局,输出一份 JSON」→ modlens。
  • 任务是长截图 OCR、把界面复原成 HTML、把图标描成 SVG → vision-tools。
  • 当前模型被用户规则禁止使用外挂视觉 → 遵守用户规则。

要用 EagleEye 的时候

  • 需要当前桌面/指定窗口的真实像素(游戏 UI、前端页面、桌面应用)。
  • 需要像素级事实:颜色、偏移、模板是否一致、回归有没有坏。
  • 需要把一次捕获的图裁开、放大、再量,并且坐标还能追回屏幕。
  • 需要量化「画质/审美」分数、做前后对比(改 UI/美术后再截一张评分,看有没有变好)→ score_imagetask=aesthetic|quality,模型 qrealign-mini 默认 / musiq-ava / nimasource_type=model_inference, 非校准概率,用于粗排与对比)。

Windows 上可以用 list_windows / capture_window / capture_window_graphics。 其它平台这些工具会返回 PLATFORM_UNSUPPORTED:改用 capture_screenload_image

调用顺序

  1. Observe:需要等界面出现或加载完成时先 wait_for_visual,再 list_windows / list_monitors(需要时)→ capture_screen / capture_window / load_image。命中后的 image_ref 可直接给后续工具,不要再截一张。
  2. Locate:已知坐标 → crop_image;已知颜色 → find_color;已知模板 → template_match;已知文字 → locate_text / ocr;只知道「是什么」→ locate_visual_element(推断,必须复核)。
  3. Verify:颜色/尺寸用 get_pixel / sample_region / measure_region;差异用 compare_images;pass/fail 用 compare_with_referencevisual_regression(动态区域配 ignore_regions);画质/审美评分用 score_image

优先级:算法视觉 > OCR > 视觉模型 > 组合工具。能算不算,能测不猜。

region 参数可传对象 {x,y,width,height},也兼容 [x,y,w,h]{w,h} 别名。

小尺寸裁剪/放大图(最长边 <512px)送 analyze_image 等前,server 会自动放大预处理 (EAGLEEYE_VISION_MIN_DIM 可配);若仍 VISION_CALL_FAILED,改用更大范围裁剪或直接对整图提问。

capture_window = 用户屏幕上实际看到的窗口(可能被遮挡)。 capture_window_graphics = 应用渲染表面(可后台),不代表用户当前看见的画面

Read the full file on GitHub · 71 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. 10d ago First seen · 71 lines · 117 tokens per session scan A 4af7b4c4f88b

Subscribe to this mod's changes

eagleeye is a skill published in the GitHub repository baimaomaomao556/eagleeye-mcp (0 stars, last pushed 26d ago), licensed MIT. It adds 117 tokens to every session and 1,218 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to eagleeye, differing in 7 lines, and is treated as a copy.

Related

Other skills, from other repositories