eagleeye

eagleeye is a skill for Claude Code, Codex from baimaomaomao556/eagleeye-mcp. It costs 117 tokens per session (1,279 once invoked), scanned A, original, 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, window captures, waiting for interfaces, OCR, pixel measurements, UI checks, and visual regression tests.
Why use it?
It provides observable facts about what is currently on screen instead of relying on assumptions. 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.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is 规范路径:[`skills/eagleeye/SKILL.md`](../skills/eagleeye/SKILL.md)(供 `npx skills add` 发现)。.

Good fit Use it for screenshots, window captures, waiting for interfaces, OCR, pixel measurements, UI checks, and visual regression tests.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

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

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/skill/github.svg)](https://agentmods.dev/skills/baimaomaomao556/eagleeye-mcp/skill)
Your own site
<a href="https://agentmods.dev/skills/baimaomaomao556/eagleeye-mcp/skill"><img src="https://agentmods.dev/badge/skills/baimaomaomao556/eagleeye-mcp/skill/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/skill"><img src="https://agentmods.dev/badge/skills/baimaomaomao556/eagleeye-mcp/skill.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 1,279 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 $0.00117 $0.01279
Opus 5 $0.00059 $0.00639
Sonnet 5 $0.00023 $0.00256
Haiku 4.5 $0.00012 $0.00128

Measured 9d ago against content hash 339ae4b74d4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 9d 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

Copies of this mod

1 near-identical copy found in the catalogue:

  • eagleeye — 86% identical, 7 lines differ
skill/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EagleEye — DSH / Agent Skills 薄包装

规范路径:skills/eagleeye/SKILL.md(供 npx skills add 发现)。 本文件与其保持同步,便于旧的 ~/.dsh/skills/eagleeye junction。

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。

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。

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

Read the full file on GitHub · 74 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. 9d ago First seen · 74 lines · 117 tokens per session scan A 339ae4b74d4a

Subscribe to this mod's changes

eagleeye is a skill published in the GitHub repository baimaomaomao556/eagleeye-mcp (0 stars, last pushed 25d ago), licensed MIT. It adds 117 tokens to every session and 1,279 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

error-handling

Patterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages. Use when designing error types, retries, circuit breakers, or user-facing failure messages in TypeScript, Python, or Go.

gongyijie85/dsh-ecc · 61 tokens

kubernetes-patterns

Kubernetes workload patterns, resource management, RBAC, probes, autoscaling, ConfigMap/Secret handling, and kubectl debugging for production-grade deployments. Use when writing or reviewing Kubernetes manifests, or debugging probes, RBAC, autoscaling, or resource limits.

gongyijie85/dsh-ecc · 58 tokens

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications…

gongyijie85/dsh-ecc · 95 tokens

click-path-audit

Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any…

gongyijie85/dsh-ecc · 71 tokens

network-config-validation

Pre-deployment checks for router and switch configuration, including dangerous commands, duplicate addresses, subnet overlaps, stale references, management-plane risk, and IOS-style security hygiene. Use when reviewing a router or switch configuration before deployment.

gongyijie85/dsh-ecc · 48 tokens

network-bgp-diagnostics

Diagnostics-only BGP troubleshooting patterns for neighbor state, route exchange, prefix policy, AS path inspection, and safe evidence collection. Use when a BGP neighbor is down, routes are missing, or prefix policy and AS path need inspection.

gongyijie85/dsh-ecc · 53 tokens