What is dym-agent-desktop-drive?

A workflow for reading and controlling macOS desktop apps through an installed agent-desktop program. It first identifies the right window and interface element, then performs actions and checks the result using stable references rather than screen coordinates.

Use it to inspect settings, find buttons or fields, type, click, and verify multi-step actions in desktop apps such as System Settings or Teams.

It helps avoid clicking the wrong window or relying on coordinates that change when an app moves. It is intended for native or Electron apps with macOS accessibility support, not ordinary web pages.

dym-agent-desktop-drive — Skill for Claude Code by Rheinmir/setup

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.

Any agent

npx skills add Rheinmir/setup --skill dym-agent-desktop-drive

Clone the repo

git clone --depth 1 https://github.com/Rheinmir/setup

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rheinmir/setup/dym-agent-desktop-drive/github.svg)](https://agentmods.dev/skills/rheinmir/setup/dym-agent-desktop-drive)

Your own site

<a href="https://agentmods.dev/skills/rheinmir/setup/dym-agent-desktop-drive"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-agent-desktop-drive/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rheinmir/setup/dym-agent-desktop-drive"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-agent-desktop-drive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,337 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.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.01337
Opus 5.5	$0.00027	$0.00535
Sonnet 5.5	$0.00013	$0.00267
Haiku 4.5	$0.00007	$0.00134

Measured yesterday against content hash 987685113273, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dym-agent-desktop-drive 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 yesterday.

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.

.overstack/doyourmagic/agent-desktop/skills/dym-agent-desktop-drive/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dym-agent-desktop-drive

When to use

Cần đọc trạng thái hoặc thao tác trong một app desktop macOS (native hoặc Electron có bật AX), nhiều bước, và muốn ref không chết giữa chừng.
Cần bằng chứng "đã bấm đúng phần tử nào" chứ không phải toạ độ mù.
Web thuần trong trình duyệt → xem /dym-agent-desktop route trước, thường playwright hoặc CDP rẻ hơn nhiều.

Steps

Đặt trước: AD=<đường dẫn binary>, export AGENT_DESKTOP_HOME=<abs>.

Chốt cửa sổ trước khi snapshot. App nhiều cửa sổ → snapshot --app trả AMBIGUOUS_TARGET kèm danh sách ứng viên (đây là tính năng, không phải lỗi):

$AD list-windows --app "Microsoft Teams"
$AD snapshot --window-id w-9249 --skeleton -i --compact

Skeleton trước, drill sau — chỉ khi app dày:

$AD snapshot --app "System Settings" --skeleton -i --compact   # đo: 4630 B, 27 ref
$AD snapshot --root "@s23de9t04j589e:e5" -i --compact           # bung đúng vùng cần

App thưa (Finder, Calculator, TextEdit) → bỏ skeleton, snapshot thẳng. Đã biết tên/role → find rẻ nhất, khỏi snapshot:

$AD find --app "System Settings" --role button --name "Sound" --exact --limit 2

Hành động bằng ref đầy đủ @<snapshot_id>:e<N> — luôn bọc nháy vì : trong shell:

$AD click "@s23de9t04j589e:e12"
$AD set-value "@s23de9t04j589e:e2" "text"
$AD toggle "@s23de9t04j589e:e6"      # hoặc check/uncheck (idempotent)
$AD select "@s23de9t04j589e:e4" "Option B"

Mặc định headless: đi đường AX ngữ nghĩa, không cướp focus, không di chuột, không tổng hợp phím. Cần gõ/kéo thật thì thêm --headed toàn cục: $AD --headed drag --from "@s..:e1" --to "@s..:e5".

Chờ trạng thái thay vì sleep:

$AD wait --element "@s..:e5" --predicate actionable --timeout 5000
$AD wait --text "Done" --app "App" --timeout 5000
$AD wait --menu --app "App"        # chờ menu bung

Verify bằng cách drill lại đúng vùng đã đổi. Ref của vùng khác vẫn sống (scoped invalidation) — không cần snapshot lại cả app.

Read the full file on GitHub · 92 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.

yesterday First seen · 92 lines · 67 tokens per session scan A 987685113273

Subscribe to this mod's changes

dym-agent-desktop-drive is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 67 tokens to every session and 1,337 once invoked, about $0.0003 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 2026-11-07.

Productivity

dym-agent-desktop-drive next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dym-agent-desktop-driveRheinmir/setup	Skill	11	20d ago	MIT	A	67	Claude Code
orbit-notionnexu-io/open-design	Skill	107k	today	Apache-2.0	A	117	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	112k	today	MIT	A	30	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	2d ago	MIT	A	184	Claude Code
rowboat-spacesrowboatlabs/rowboat	Skill	18k	today	Apache-2.0	A	60	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	today	MIT	A	33	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	11d ago	MIT	A	52	Claude Code, Codex

dym-agent-desktop-drive

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

dym-agent-desktop-drive

When to use

Steps

What this file has done since we first saw it

dym-agent-desktop-drive compared with skills from other repositories