using-vision

Instructions for locating and clicking visible items in applications when normal accessibility information cannot find them. It uses screen pixels, visible text, or image matching.

In plain words
What is it for?
Clicking buttons and other controls in web pages, canvas interfaces, Electron or Flutter apps, and games.
Why use it?
Some web pages, games, and apps do not expose their controls to standard automation tools, so these instructions provide a fallback for finding them on the screen.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/metahub-tech/agent-fleet/using-vision
Any agent
npx skills add metahub-tech/agent-fleet --skill using-vision
Clone the repo
git clone --depth 1 https://github.com/metahub-tech/agent-fleet

Made for: Claude Code, Codex.

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,059 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00077 $0.01059
Opus 5 $0.00039 $0.00530
Sonnet 5 $0.00015 $0.00212
Haiku 4.5 $0.00008 $0.00106

Measured 2d ago against content hash 71d732a6cb43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-vision 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 2d 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.

platforms/macos/skills/using-vision/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using vision (像素级元素定位)

vision 是 pc-device(mac-device / win-device)的能力模块,补 element-action 的盲区:find_elements/tap_element 走 OS 无障碍树(AX/UIA),但网页、canvas、Electron(关 a11y)、Flutter、游戏的内容不在树里 → 它们返回空。这时用 vision 按像素定位。

何时用 vision(决策)

要点一个元素
  │
  ├─ 原生 app 控件? → 先 find_elements / tap_element(AX/UIA,更准更省,抗布局漂移)
  │
  └─ 网页 / canvas / Electron / Flutter / 游戏(a11y 树拿不到)?
        → vision_locate / vision_tap(像素,本节)

不要一上来就 vision。无障碍树能拿到就用 element-action。vision 是树失效时的 fallback。

三个工具

坐标都和 core tap 同一点空间——定位完直接能点。

vision_locate(query) — 按可见文字定位

vision_locate("登录")
→ {"ok": true, "count": 2, "candidates": [
     {"text": "登录", "center": [1200, 29], "box": [...], "score": 1.0, "match_field": "exact"}, ...]}
  • 返回排序候选(exact > 前缀 > 包含)。先 locate 看清候选,再决定点哪个。
  • region=(left, top, right, bottom):只搜这块区域(强烈建议——密集页全屏 OCR ~1–2s,裁剪到亚秒)。
  • 没找到 → count:0 + ocr_sample(当时读到的文本),据此换词/缩 region。

vision_tap(query) — 找到即点

vision_tap("登录")                  # 唯一/exact 命中 → 直接点
vision_tap("hide", nth=2)           # 多命中时 nth(0-based)指定第几个
vision_tap("提交", region=(300,500,460,560))
  • nth:0-based(0=最优候选);省略=自动(唯一或 exact 即点;多个歧义则不点、返回候选让你加 nth 或更具体的 query)。与 tap_element 同语义。
  • 歧义返回 {"ok": false, "error": "ambiguous", "candidates": [...]} → 传 nth。

vision_locate_image(template) — 按图标图定位(无字元素)

vision_locate_image(template_b64="<截图的 base64>")
vision_locate_image(template_path="/path/on/host/icon.png", threshold=0.9)
→ {"ok": true, "found": true, "center": [x, y], "score": 0.97}
  • 给一张图标/按钮的小图,返回它在屏上的中心。用于没有文字的纯图标按钮(工具栏 icon 等)。
  • 单尺度:模板必须按当前显示缩放截取;跨 DPI/缩放会掉置信度(found:false + best_score + hint)。

红线 / 边界(重要)

  • vision 只管「定位」,不是全屏 OCR、不负责「读懂页面」。 要理解页面内容、读低对比的次要文字(灰色元数据、说明文字),用 take_screenshot 交给你自己的视觉——那是你的强项,vision 的 OCR 在低对比文字上会漏。
  • vision 擅长高对比可交互元素(按钮/链接/标题/菜单)的精确定位(~个位 px);低对比装饰文字定位不到很正常,不是 bug。
  • 模板匹配跨 DPI 是已知短板(单尺度)。

典型流程(网页点登录)

1. find_elements("登录")        # web → 空(AX 树没有)
2. vision_locate("登录")        # 看候选、确认 center 落在按钮上
3. vision_tap("登录")           # 点中

全程 0 LLM token、离线、纯 CPU。

Read the full file on GitHub · 69 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. 2d ago First seen · 69 lines · 77 tokens per session scan A 71d732a6cb43

Subscribe to this mod's changes

using-vision is a skill published in the GitHub repository metahub-tech/agent-fleet (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,059 once invoked, about $0.0004 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

dingtalk_channel_connect

Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.

agentscope-ai/QwenPaw · 69 tokens

dingtalk_channel_connect

使用可视浏览器自动完成 QwenPaw 的钉钉频道接入。适用于用户提到钉钉、DingTalk、开发者后台、Client ID、Client Secret、机器人、Stream 模式、绑定或配置 channel 的场景;支持遇到登录页时暂停,等待用户登录后继续。.

agentscope-ai/QwenPaw · 78 tokens

browser_cdp

Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit cdpport only when the user wants another local tool to attach.

agentscope-ai/QwenPaw · 70 tokens

browser_cdp

当用户明确希望连接到已运行的 Chrome 浏览器、扫描本地 CDP 端口、显式指定 cdpport,或让多个 agent / 工具共享同一个浏览器时,使用本 skill。browser 默认不开放调试端口;仅当用户明确希望其他本地工具附加时才显式传入 cdpport。.

agentscope-ai/QwenPaw · 85 tokens

browser_visible

当用户需要控制 browser 的浏览器启动方式时,使用本 skill。browser 默认由 Playwright 直接管理、不开放调试端口(需让其他本地工具附加时显式传 cdpport);headed 控制是否显示窗口,privatemode 保留用于兼容、不再改变默认行为,browserargs 传入额外的 Chromium 启动参数,executablepath 指定自定义浏览器可执行文件路径。.

agentscope-ai/QwenPaw · 108 tokens

browser_visible

Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…

agentscope-ai/QwenPaw · 75 tokens