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 agentmods add skills/superagent-ai/grok-cli/agent-desktopnpx skills add superagent-ai/grok-cli --skill agent-desktopgit clone --depth 1 https://github.com/superagent-ai/grok-cliWrote 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/superagent-ai/grok-cli/agent-desktop)<a href="https://agentmods.dev/skills/superagent-ai/grok-cli/agent-desktop"><img src="https://agentmods.dev/badge/skills/superagent-ai/grok-cli/agent-desktop.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00615 |
| Opus 5 | $0.00028 | $0.00308 |
| Sonnet 5 | $0.00011 | $0.00123 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
agent-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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-desktop
Use this skill when the task involves the host macOS desktop rather than repository files, shell output, or browser-only verification.
This project uses agent-desktop on the host. Prefer the built-in Computer sub-agent for these tasks instead of trying to drive the desktop with plain shell commands.
When to use it
- The user wants to inspect or interact with a native macOS application.
- The task needs app launch, window focus, accessibility snapshots, semantic element refs, clicks, typing, keypresses, or scrolling.
- A browser-only workflow is not enough, or the target is not a web page.
Requirements
agent-desktopmust be installed and its native binary available.- On macOS, the terminal app running
grokneeds Accessibility permission. - Refs from
computer_snapshotare only valid until the next snapshot.
Preferred flow
- Delegate to
taskwithagent: "computer"unless the current agent already has thecomputer_*tools and the task is tiny. - Use
computer_launch,computer_list_windows, orcomputer_focus_windowto get the target app/window ready. - Start with
computer_snapshot. - Pick one ref-based action.
- After any UI transition, snapshot again before reusing refs.
Tool guidance
computer_snapshot: primary observation tool; preferinteractive_only.computer_click: userefvalues from the latest snapshot whenever possible.computer_type: requires a target ref and is preferred over coordinate typing.computer_press: use for shortcuts and special keys such asEnter,Tab,cmd+space, orcmd+k.computer_scroll: pass an element ref, not raw coordinates.computer_get: read text, value, bounds, role, or states from a ref.computer_screenshot: use for visual confirmation or when the accessibility tree is not enough.
Reliability rules
- Use a snapshot -> act -> snapshot loop.
- Prefer refs over coordinates.
- Refs go stale after the next snapshot; do not reuse them blindly.
- Keep actions reversible and low risk unless the user explicitly asked for something destructive.
- If the accessibility tree is poor or ambiguous, use
computer_screenshotfor confirmation and explain the limitation.
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.
- 3d ago First seen · 59 lines · 56 tokens per session scan A 5b817bb2fa21
agent-desktop is a skill published in the GitHub repository superagent-ai/grok-cli (3,445 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 615 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
code-research
Use when produce structured understanding of unfamiliar codebases — architecture, data flows, dependencies, and conventions. Use when joining a new project, tracing feature implementations, or mapping system architecture.
code-agent
Use when implementing features from specs — reads requirements, writes code with tests, iterates until verification passes.
trellis-finish-work
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
workspace-digest
Summarize the files saved in this assistant's shared workspace. Use when the user asks what is in their workspace, for a file inventory, or a digest of saved work.