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.
npx skills add uvwt/agentdock-skills --skill desktopgit clone --depth 1 https://github.com/uvwt/agentdock-skillsWrote 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/uvwt/agentdock-skills/desktop)<a href="https://agentmods.dev/skills/uvwt/agentdock-skills/desktop"><img src="https://agentmods.dev/badge/skills/uvwt/agentdock-skills/desktop/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/uvwt/agentdock-skills/desktop"><img src="https://agentmods.dev/badge/skills/uvwt/agentdock-skills/desktop.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 | $0.00013 | $0.00572 |
| Opus 5.5 | $0.00005 | $0.00229 |
| Sonnet 5.5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
desktop 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 28d 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.
What it actually says
macOS Desktop Skill
AgentDock 的 macOS 桌面自动化能力已经从 core 工具拆分为此 Skill 工作流。
调用入口
skill_action=observe：action=preflight | list_apps | app_state | window_list | snapshot | snapshot_app。skill_action=act：action=focus | move | click | double_click | scroll | drag | type | set_value | secondary_action | hotkey | wait。skill_action=clipboard-read/skill_action=clipboard-write：读写剪贴板。
数据目录
截图原始文件写入 SKILL_DATA_DIR/artifacts；AgentDock managed 运行时由宿主注入私有 SKILL_DATA_DIR，其他宿主使用 XDG 状态目录作为 fallback。snapshot / snapshot_app 同时发布到 AGENTDOCK_HOME/public-artifacts，并返回包含 artifact_id 的轻量 screenshot 引用。配置 AGENTDOCK_SERVER_URL 时额外返回带过期时间的签名 screenshot.url。需要模型查看图片时，再调用 AgentDock view_image(artifact_id=...)；Desktop Skill 不直接返回 Base64。
- 动作参数不支持别名：
skill_action=act必须使用action枚举值；secondary_action的辅助动作名必须放在ax_action；wait使用ms。
辅助脚本执行
Skill 本体是本说明文档。确需调用包内辅助脚本时，在 Skill 包根目录使用相对路径执行；运行宿主负责切换到包根目录并把所需变量注入当前子进程。
printf '%s' '{"skill_action":"<动作>"}' | python3 run.py
输入必须是 JSON 对象。写操作仍按本文档中的确认规则执行。
| 动作 | 用途 |
|---|---|
status |
Run a desktop preflight check and report desktop automation readiness. |
observe |
Unified macOS desktop observation action: preflight, list_apps, app_state, window_list, snapshot, or snapshot_app. |
act |
Unified macOS desktop action: focus, move, click, double_click, scroll, drag, type, set_value, secondary_action, hotkey, or wait. |
clipboard-read |
Read macOS clipboard text. |
clipboard-write |
Write macOS clipboard text and optionally verify by reading it back. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 28d ago Changed fb946ea65abb
- 29d ago Changed · -1 lines 7a4d52153c27
- 1mo ago First seen · 40 lines · 13 tokens per session scan A 6dda4776f1c6
desktop is a skill published in the GitHub repository uvwt/agentdock-skills (6 stars, last pushed 8d ago), licensed Apache-2.0. It adds 13 tokens to every session and 572 once invoked, about $0.0001 per session on Opus 5.5. 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
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.
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.
browser_cdp
Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.
browser_visible
Browser launch controls for choosing whether a Chromium-based browser window is visible, which browser program to run, and which startup options to pass.
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…
skill-body
Call help() or help("page.click") to print signatures and uncommon options of APIs named below; it prints by itself, so do not wrap it in console.log. For installation or connection problems, read references/install.md in the ego-browser Skill directory.