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 Rheinmir/setup --skill dym-agent-desktop-installgit clone --depth 1 https://github.com/Rheinmir/setupWrote 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/rheinmir/setup/dym-agent-desktop-install)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-agent-desktop-install"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-agent-desktop-install/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/rheinmir/setup/dym-agent-desktop-install"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-agent-desktop-install.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 | $0.00060 | $0.00912 |
| Opus 5.5 | $0.00024 | $0.00365 |
| Sonnet 5.5 | $0.00012 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade C, and why
dym-agent-desktop-install scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`npm uninstall -g agent-desktop` rồi `rm -rf ~/.agent-desktop`. How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dym-agent-desktop-install
When to use
- Sắp dùng
agent-desktoplần đầu trên máy này, hoặc CI macOS runner cần nó. - Lệnh bất kỳ trả
PERM_DENIED→ quay lại đây kiểm quyền. - KHÔNG dùng trên Linux/Windows: postinstall khai
SUPPORTED_PLATFORMS = ['darwin']và sẽ bỏ qua; cratewindows/linuxlà stub 76 dòng trảPLATFORM_NOT_SUPPORTED.
Steps
- Cài có pin scope — không để installer ghi vào
$HOMEthật:
S=./scratchpad/agent-desktop-probe && mkdir -p $S/{home,prefix}
HOME=$S/home npm install -g --prefix $S/prefix agent-desktop
AD=$S/prefix/bin/agent-desktop
Đo 2026-09-09: rc=0, ~4s, $S/home chỉ mọc thêm .npm/ (cache) — không đụng gì khác.
bin/ chứa agent-desktop-darwin-arm64 (3.0M) + agent-desktop-macos-helper (498K).
Cài thật cho cả máy thì bỏ --prefix và HOME= — chỉ làm khi user đồng ý.
- Tách state ra khỏi
~/.agent-desktop— mọi snapshot/session/trace nằm dưới đây:
export AGENT_DESKTOP_HOME=$PWD/scratchpad/agent-desktop-state # PHẢI tuyệt đối
Giá trị tương đối hoặc rỗng → INVALID_ARGS trước khi lệnh chạy. status in lại ở
data.state_root. Đường dẫn output tường minh (screenshot --out, --trace <path>)
KHÔNG bị dời gốc.
- Xác minh — ba lệnh, đều phải rc=0:
$AD version # {"version":"2.3","ok":true,...,"data":{"os":"macos","target":"aarch64","version":"0.8.5"}}
$AD permissions # accessibility.state + screen_recording.state phải là "granted"
$AD status # thêm state_root, session_id, supported_surfaces
- Nếu quyền chưa cấp:
$AD permissions --request # bật dialog hệ thống trong helper cô lập
Cấp cho ứng dụng terminal đang chạy lệnh (iTerm2/Terminal/VS Code), không phải cho binary. Sau khi cấp phải thoát hẳn và mở lại terminal — TCC chỉ đọc lúc tiến trình khởi động. Screenshot cần thêm Screen Recording.
- Gỡ: xoá
$Slà xong (binary + state đều nằm trong đó). Bản cài toàn máy:npm uninstall -g agent-desktoprồirm -rf ~/.agent-desktop.
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 · 67 lines · 60 tokens per session scan C d1ca6ce32e76
dym-agent-desktop-install is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 60 tokens to every session and 912 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.
dym-agent-desktop-install compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-agent-desktop-installRheinmir/setup | Skill | 11 | 20d ago | MIT | C | 60 | 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 |