What it does
Lets a coding agent see the web UI it just changed: findings as text, motion included.
- Connects 在你的电脑上运行
- Account or key No key needed
- Category 开发者工具
可搭配使用
教 AI 做这类工作的 Skill,可与本项一起使用
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
为什么排在这里
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 7/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 19/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
安装
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Agent Eyes。按照 https://mcp.popnx.com/i/muhlegger-agent-eyes.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月17日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要先在电脑上安装 Node.js(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
让 AI 帮你安装
把这段话复制到 Claude 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude 安装 MCP server Agent Eyes,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "agent-eyes": { "command": "npx", "args": [ "-y", "@muhlegger/agent-eyes", "mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Agent Eyes 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 Node.js(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -v- 显示版本号(例如 v26.13.1)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
node -v安装一次,所有需要 Node.js 的工具都能用
打开电脑版 Claude 应用的设置文件
SettingsDeveloperEdit Config
粘贴这些设置并保存文件
{ "mcpServers": { "agent-eyes": { "command": "npx", "args": [ "-y", "@muhlegger/agent-eyes", "mcp" ] } } }退出 Claude 再重新打开
试一试
用 Agent Eyes 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Agent Eyes,或回答中出现 Agent Eyes 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Agent Eyes
Agent Eyes 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
你可以改用这些方式
A · 使用能连接 Agent Eyes 的应用
- 需要先在电脑上安装 Node.js(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
- 需要先在电脑上安装 Node.js(只需一次)
- 需要先在电脑上安装 Node.js(只需一次)
- 需要先在电脑上安装 Node.js(只需一次)
B · 开发者工具 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
- Sentry✓ ChatGPT
- Compiler Explorer✓ ChatGPT
- GitDiagram✓ ChatGPT
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
让 AI 帮你安装
把这段话复制到 Claude Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude Code 安装 MCP server Agent Eyes,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):claude mcp add --scope user agent-eyes -- npx -y @muhlegger/agent-eyes mcp 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Agent Eyes 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 Node.js(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -v- 显示版本号(例如 v26.13.1)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
node -v安装一次,所有需要 Node.js 的工具都能用
打开终端
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
粘贴这条命令并按 Enter
claude mcp add --scope user agent-eyes -- npx -y @muhlegger/agent-eyes mcp在 Claude Code 中输入 /mcp
应能看到 Agent Eyes 在列表中并显示已连接
试一试
用 Agent Eyes 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Agent Eyes,或回答中出现 Agent Eyes 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
让 AI 帮你安装
把这段话复制到 Cursor 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Cursor 安装 MCP server Agent Eyes,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "agent-eyes": { "command": "npx", "args": [ "-y", "@muhlegger/agent-eyes", "mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Agent Eyes 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 Node.js(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -v- 显示版本号(例如 v26.13.1)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
node -v安装一次,所有需要 Node.js 的工具都能用
在 Cursor 中以 Agent 模式打开 AI 聊天
试一试
用 Agent Eyes 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Agent Eyes,或回答中出现 Agent Eyes 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
让 AI 帮你安装
把这段话复制到 VS Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 VS Code 安装 MCP server Agent Eyes,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "servers": { "agent-eyes": { "type": "stdio", "command": "npx", "args": [ "-y", "@muhlegger/agent-eyes", "mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Agent Eyes 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 Node.js(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -v- 显示版本号(例如 v26.13.1)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
node -v安装一次,所有需要 Node.js 的工具都能用
在 VS Code 中以 Agent 模式打开 AI 聊天
试一试
用 Agent Eyes 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Agent Eyes,或回答中出现 Agent Eyes 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
开发者专用:终端命令和 JSON 设置
安装在电脑上
Claude Code
claude mcp add --scope user agent-eyes -- npx -y @muhlegger/agent-eyes mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"agent-eyes": {
"command": "npx",
"args": [
"-y",
"@muhlegger/agent-eyes",
"mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"agent-eyes": {
"command": "npx",
"args": [
"-y",
"@muhlegger/agent-eyes",
"mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"agent-eyes": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@muhlegger/agent-eyes",
"mcp"
]
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
一览
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它能做什么
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月19日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 muhlegger 验证,该账户拥有此仓库
- ✓ 通过
仍在维护
代码最后更新于前天
- ✓ 通过
有许可证
使用 MIT
- – 不适用
端点有响应
它在你的电脑上运行,没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行,改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行;我们只能读取互联网端点的工具列表
已公开的漏洞(OSV.dev)
尚未检查
作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/muhlegger-agent-eyes)讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“开发者工具”中的其他服务器比较i
- 星标数多于此分类中其他 6182 个服务器的 81%
- 发布到注册中心的时间比此分类中其他 6182 个服务器的 92% 更新
- 基础检查结果等于或优于此分类中其他 6182 个服务器的 99%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
Agent Eyes 安全吗?
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
它还在维护吗?
GitHub 仓库最后更新于前天,最新版本(0.3.3)于前天进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
有什么可以替代它?
同一分类中有:GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
功能相近的其他选择
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
GitDiagram
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
Appllama
Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Omnara
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Repowise
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
| 本项 Agent Eyes | GitDiagram | Appllama | Cloudflare MCP | Omnara | Repowise | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 云端或安装在电脑上都可以 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 是 | 否 | 否 |
| 基础检查 | 3/3 | 4/4 | 4/4 | 4/4 | 4/4 | 5/5 |
| 许可证 | MIT | MIT | MIT | Apache-2.0 | Apache-2.0 | AGPL-3.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
agent-eyes
Stop being your agent's eyes.
Your coding agent says "done" about a screen it never saw. Then you open the page, notice the panel that snaps instead of sliding, describe it badly, and wait for another round.
agent-eyes gives the agent that look, motion included. One shell command takes the screenshots (logged in, at every width, after clicks and hovers) and hands back what is wrong as text: an animation that squeezes, flickers, snaps or freezes, content that jumps after load, a page that scrolls sideways on a phone. The agent reads a few lines and opens an image only when it has to.
The tool lines and both frame strips are real output from the bundled demo page, shortened. The chat lines around them are staged.
Português abaixo · Benchmark · MIT · Node 18+ · local, no cloud
Use it from: a shell command · a Claude Code plugin · an MCP server for Cursor, Windsurf and others
Sound familiar?
Almost every change an agent makes to a web app ends up on a screen, and someone has to look at it. Today that someone is you.
| Your day now | With agent-eyes |
|---|---|
| The agent says "done". You open the page and it isn't. | The agent looks before it says "done", and reads what is wrong. |
| You take a screenshot, paste it, describe the problem ("it kind of jumps"), wait, and repeat. | The agent takes its own screenshots, logged in. The problem comes back as a sentence with numbers: width jumped from 0 to 252 px in a single frame. |
| It walks past things anyone would see: content that jumps after load, a page that scrolls sideways on a phone, an error on the page. | Every run reports them as text, whether or not anyone asked. |
| Animations are invisible to it. A screenshot is a still, and a transition that never runs looks perfect before and after. | The motion is recorded at real speed and measured: shrink-and-return, snap, flicker, freeze. |
| When the agent does look, it writes a throwaway script first. In my sessions that took a median of 1.2 min per look, and one script in five was rewritten before it showed anything. | One command. The login lives in a config file, once. |
| Screenshots pile up in the conversation and are re-read on every later step. | Text first. Each image is listed with its token cost, and identical means there is nothing to open. |
What it does not do is make a design beautiful: taste stays with you. It takes away the rounds you spend on what is broken, so the rounds you do spend are about the design.
- Measured on a real codebase, it found more, faster and cheaper. Same task, same model, with and without it: 6 of 9 planted defects found instead of 4 of 9, in 22% less time and for 23% less money, with zero throwaway scripts (details).
- Works with the agent you already use. A Claude Code plugin, an MCP server (Cursor, Windsurf, Claude Desktop, ...) and a block for
AGENTS.md(Codex, Gemini CLI, ...). Only dependency: Playwright. Runs locally, nothing leaves your machine.
Quickstart (30 seconds)
npm install -g @muhlegger/agent-eyes
agent-eyes install # downloads Chromium once (add --with-deps on a fresh Linux) agent-eyes http://localhost:3000 /settings --widths 1440,390
Or without installing: npx -y @muhlegger/agent-eyes http://localhost:3000 /settings. (The package is @muhlegger/agent-eyes; the unscoped agent-eyes on npm is unrelated.)
Then tell your agent it exists. Pick one:
Claude Code
/plugin install agent-eyes --marketplace muhlegger/agent-eyes
On versions before 2.1.275: /plugin marketplace add muhlegger/agent-eyes, then /plugin install agent-eyes@agent-eyes. The plugin is one skill: Claude reaches for agent-eyes after a visual change instead of writing a Playwright script. Prefer a plain file in one project? mkdir -p .claude/skills/agent-eyes && agent-eyes skill > .claude/skills/agent-eyes/SKILL.md.
Cursor, Windsurf, Claude Desktop, any MCP client
{
"mcpServers": { "agent-eyes": { "command": "agent-eyes", "args": ["mcp"] } } }
(Without a global install: "command": "npx", "args": ["-y", "@muhlegger/agent-eyes", "mcp"].)
In .cursor/mcp.json (Cursor), ~/.codeium/windsurf/mcp_config.json (Windsurf) or your client's MCP settings. Three tools: check_ui (the whole check in one call, findings as text), view_image (open one of the images it listed, only when needed) and compare_images. Images are never pushed into the conversation: the agent asks for the ones it wants, knowing what each costs.
Codex, Gemini CLI and other agents with a shell
agent-eyes skill >> AGENTS.md
What it catches
| You changed... | agent-eyes tells the agent |
|---|---|
| An animation or transition | it shrank and came back, snapped (a size that jumps in one frame: the transition is written but not running), flickered, disappeared, left its path, or the browser froze (above ~50 ms is felt) |
| A page that loads data | which elements jumped after load, and by how much |
| A layout | horizontal scroll on a phone, at every width you asked for |
| Anything | page errors, console errors, requests that failed (404, 5xx), actions that missed their target |
| A theme | the same screen in dark or light, or with reduced motion (--color-scheme dark, --reduced-motion) |
| A screen, compared with before | identical (nothing to open), or one image with each changed region boxed in red, listed as text |
Where it fits in your day
It is one command, so it goes wherever a command goes.
| When | How | What comes back |
|---|---|---|
| The agent changed a screen | The plugin, the MCP server or the AGENTS.md block: the agent runs it before saying "done" | What is wrong, as text. This is what it was built for. |
| A refactor that should change nothing | -o /tmp/before, refactor, then --compare /tmp/before | identical, or each changed region boxed in red |
| "Does it work on a phone?" | --widths 1440,768,390 | Sideways scroll and cut-off content, per width |
| A gate in a pre-commit hook or in CI | --strict | Exit code 1 when anything is found |
| A trigger in Claude Code | A Stop hook around --strict | The turn cannot end while the screen is broken |
The trigger is a few lines of shell. When the agent touched UI files and tries to finish, the hook looks at the screens you listed. If something is wrong, Claude Code sends the findings back as the agent's next input:
Stop hook feedback:
glitch@1280 motion: 21 distinct frames over 508 ms ! the browser froze for 126 ms while animating (noticeable above ~50 ms) ! width shrank from 280 to 200 px mid-motion and came back (see the frames)
That is real output, shortened, from the bundled demo page with its planted glitch. With the screen clean, the turn ends as usual.
Why an agent needs a look it can run
Anthropic's guide to Claude Code puts the problem this way (Give Claude a check to run):
Claude stops when the work looks done. If it has nothing to run that tells it whether the work actually
*is* done, "looks done" is all it has to go on. In practice that makes you the test suite, and every
mistake sits there until you happen to notice it.
The guide lists a browser screenshot among the checks, next to tests and linters. Anthropic's engineers ran into the same thing building apps with long-running agents: "agents reliably skew positive when grading their own work", and apps "often looked impressive but still had real bugs when you actually tried to use them", so they gave the reviewing agent a browser to use the live page before scoring (Harness design for long-running application development, March 2026).
For code, the check is a test. For a screen, the check is looking, and looking is the expensive one:
- The agent writes a script for every look. The scripts work; the cost is in the repetition. In three weeks of my own sessions on one project: ~210 throwaway Playwright scripts, ~200 of them re-implementing the login. Across 166 of them, it took a median of 1.2 min (mean 3.3) from starting the script to seeing the image; 44 ran more than once and 33 were rewritten (the login, a selector, a server still compiling).
- A screenshot is a still. A transition that never runs looks perfect in the before and in the after.
- Images are heavy. Each one stays in the conversation and is re-read on every later step.
agent-eyes is that look made cheap: one command, the answer as text, pass or fail with --strict.
Neither source puts a number on how much a check helps. The only numbers on this page are mine, from a small sample, below. agent-eyes is not affiliated with Anthropic.
The bug that shipped
On a real product, a side panel was meant to slide open. The width transition was written in the CSS, but a later transition: rule on the same element replaced the property list, so the column snapped open in a single frame while its content faded in. The code reads as animated; only watching it shows it isn't. It reached the product owner, who had to describe it ("it kind of jumps, I can't explain it") and wait for another round.
In the benchmark below, the same defect was planted again, and none of the six agent runs (three with v0.1.1, three without) reported it. Since v0.2, agent-eyes says it in one line:
panel@1536 motion: 22 distinct frames over 459 ms
! width jumped from 0 to 252 px in a single frame while other things animated: if it should slide, its transition is not running (often a later "transition:" rule on the same element replaces the property list)
Checked on that exact defect, and on the fixed version of the same screen, which it reports clean. The benchmark numbers below were measured before this detection existed.
Measured on a real project
A production Next.js app (a few hundred components), on an isolated copy with its own database reset before every run. Three defects planted in a calendar screen; the prompt named the parts that changed and the interactions to check, never a defect. Two interactions had to be reported clean. Claude Code with Opus 5.5 at high effort, 3 runs per side, answer key written before the runs, blind grading checked by hand.
| Without agent-eyes | With agent-eyes (v0.1.1) | |
|---|---|---|
| Defects found | 4 of 9 | 6 of 9 |
| False alarms | 0 | 0 |
| Time (median) | 5.0 min | 3.9 min |
| Cost (median) | $0.97 | $0.75 |
| Throwaway scripts written | 3 | 0 |
- Content that jumped after load was found in 3 of 3 runs with agent-eyes (it is reported as text) and 1 of 3 without.
- Cut-off controls on a phone, visible in any screenshot, were found by every run.
- Three runs per side is a small sample: the direction is consistent, the sizes are not precise.
On a small demo app whose code the agent can read in full, every arm found every defect, and a plain checklist in the prompt was as good as the tool. The full methodology, both benchmarks, the raw results and how