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.
git clone --depth 1 https://github.com/baimaomaomao556/eagleeye-mcpnpx agentmods add skills/baimaomaomao556/eagleeye-mcp/skillWrote 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/skills/baimaomaomao556/eagleeye-mcp/skill)<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.
<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>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 5.1 | $0.00117 | $0.01279 |
| Opus 5 | $0.00059 | $0.00639 |
| Sonnet 5 | $0.00023 | $0.00256 |
| Haiku 4.5 | $0.00012 | $0.00128 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- eagleeye — 86% identical, 7 lines differ
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/eagleeyejunction。
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
- 你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_image(task=aesthetic|quality,模型qrealign-mini默认 /musiq-ava/nima;source_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_screen 或 load_image。
调用顺序
- 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。 - 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)。 - Verify:颜色/尺寸用
get_pixel/sample_region/measure_region;差异用compare_images;pass/fail 用compare_with_reference或visual_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] 与 {w,h} 别名。
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.
- 9d ago First seen · 74 lines · 117 tokens per session scan A 339ae4b74d4a
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.
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.
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.
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…
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…
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.
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.