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 metahub-tech/agent-fleet --skill using-macgit clone --depth 1 https://github.com/metahub-tech/agent-fleetWrote 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/metahub-tech/agent-fleet/using-mac)<a href="https://agentmods.dev/skills/metahub-tech/agent-fleet/using-mac"><img src="https://agentmods.dev/badge/skills/metahub-tech/agent-fleet/using-mac/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/metahub-tech/agent-fleet/using-mac"><img src="https://agentmods.dev/badge/skills/metahub-tech/agent-fleet/using-mac.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 | $0.00056 | $0.02669 |
| Opus 5.5 | $0.00022 | $0.01068 |
| Sonnet 5.5 | $0.00011 | $0.00534 |
| Haiku 4.5 | $0.00006 | $0.00267 |
Grade A, and why
using-mac scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# 1. Strip Gatekeeper quarantine if downloaded via browser/Safari (curl How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using mac-device
Drive a remote Mac test machine via the mac-device MCP server (FastMCP, streamable-http on Tailscale, port 8767). Multi-client native; advisory single-holder coordination; 41 tools spanning state / screen / mouse / keyboard / process / file / search / zsh / AppleScript.
Critical patterns
Screenshot pixels == click pixels (logical / point space)
take_screenshot is sized to logical pixels (e.g. 1440x900 on a Retina MacBook), matching tap(x, y) and get_screen_size. So coordinates from a screenshot can be passed directly to tap without scaling. This is implemented server-side: the raw ImageGrab capture is physical (2880x1800) but the tool resizes before returning.
get_screen_size # {"width": 1440, "height": 900} -- logical
take_screenshot # PNG also at 1440x900
tap(x=720, y=450) # center; same space as screenshot
If taps miss anyway: usually a permission issue, NOT a coordinate issue. Verify Accessibility is granted (System Settings > Privacy & Security > Accessibility shows Python.app, switch on).
macOS modifiers: cmd, not ctrl
press_key("cmd+s") saves; press_key("cmd+space") opens Spotlight. paste_text already uses Cmd+V internally. Modifier aliases:
| You write | pyautogui receives |
|---|---|
cmd |
command |
option / alt |
option |
ctrl |
ctrl |
shift |
shift |
Long-running tasks: start_process, NOT run_shell
run_shell caps at 60s (max 600s). For builds, installs, slow networks:
{pid} = start_process(command="...", shell="zsh")
read_process_output(pid=..., offset=-200, length=200) # tail; poll periodically
force_terminate(pid) # if abandoned
list_sessions() # see all started_process slots
run_shell is fine for one-shot < 60s commands like date, port checks, simple file moves.
Controlling other apps: run_applescript
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.
- 1mo ago First seen · 189 lines · 56 tokens per session scan A 7b3ead2d98c1
using-mac is a skill published in the GitHub repository metahub-tech/agent-fleet (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 2,669 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
langbot-testing
Test LangBot WebUI and core product flows with an automated browser and backend logs. Use when validating the configured LangBot frontend, pipeline Debug Chat, model provider setup and test buttons, bot and knowledge-base UI flows, or troubleshooting failed LangBot end-to-end tests.
app_verification
Verify a newly created or newly installed Rome app after coding:appcreation or coding:workflowcreation finishes installing it. Use only as a second-pass verifier: receive the app id, source root, expected behavior, and local dashboard/API base URL from the creator, then visit the installed app, exercise its safe…
zafiro-qa
An Android quality-assurance workflow for testing the Zafiro app on a real phone or emulator. It uses one installed app as the test controller and a separate debug app as the app under test, with screenshots, device actions, settings, and logs.
local-test
Build, run, and test IronClaw locally using Docker containers and Chrome MCP browser automation.
knowledge-engineering-quality-and-delivery-real-api-qualification-and-e2e
A guide to tests that call real AI providers and verify complete user flows across the CLI, web interface, terminals, and ACP hosts.