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 edosulai/silenthand-cua --skill silenthandgit clone --depth 1 https://github.com/edosulai/silenthand-cuaWrote 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/edosulai/silenthand-cua/silenthand)<a href="https://agentmods.dev/skills/edosulai/silenthand-cua/silenthand"><img src="https://agentmods.dev/badge/skills/edosulai/silenthand-cua/silenthand/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/edosulai/silenthand-cua/silenthand"><img src="https://agentmods.dev/badge/skills/edosulai/silenthand-cua/silenthand.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 | $0.00070 | $0.04921 |
| Opus 5 | $0.00035 | $0.02461 |
| Sonnet 5 | $0.00014 | $0.00984 |
| Haiku 4.5 | $0.00007 | $0.00492 |
Grade B, and why
silenthand scanned grade B 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 8d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
(non-TTY: the CLI prompts “Enable all tools?” and cancels on EOF unless you How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/silenthand
Unofficial research host for OpenAI Computer Use. Ready on macOS; Windows
and Linux are in development. The host MCP
auto-detects stdio dialect: NDJSON for Hermes Agent (mcp.client.stdio)
and Content-Length for VS Code / Claude Desktop. The CUA binary also
speaks NDJSON — that is a separate client, not the host server. Prefer MCP
tools when they are attached. The CLI is node cli.mjs from a checkout
(doctor / setup / fetch-runtime / install-skill).
This is not a published npm package. Do not npx silenthand. Do not
invent WhatsApp/Telegram send/search tools. Official messages mcp (Apple
Messages: find_chats / read_messages / search_messages /
send_message / count_message_activity / read_image) is forwarded from
the binary when it answers — do not author a HOST schema for it. Do not
start ChatGPT.app or ./run-silenthand.sh unless the user asked.
On Hermes Agent, MCP tools show up two ways:
- native prefix
mcp_silenthand_* - desktop deferred
mcp__silenthand__*(double underscore) viatool_describe/tool_call
If neither skill nor MCP is attached, tell the user to run
node cli.mjs fetch-runtime (needs ChatGPT for Mac; binaries are not in git),
then node cli.mjs setup from a checkout, then:
printf 'Y\n' | hermes mcp add silenthand --command /ABSOLUTE/PATH/TO/silenthand-cua/mcp-wrapper.sh
(non-TTY: the CLI prompts “Enable all tools?” and cancels on EOF unless you
pipe Y). Verify with both hermes mcp list and
hermes config get mcp_servers.
Config persist ≠ this chat has the tools. After a successful add:
setup_mcp(server='silenthand', action='enable')injects them into the current desktop session (cataloginstallcannot attach a local stdio wrapper).- If enable is unavailable, restart Hermes /
/reload-mcp.
The wrapper does not start the CUA service. First tool call:
silenthand_doctor. If ready=false, explain userMessage and follow
agentNextSteps. Do not start extra services unless the user asked.
What ships with it
2 files 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.
- 8d ago Changed · +199 lines · +10 tokens per session be04b5831640
- 11d ago First seen · 126 lines · 60 tokens per session scan B 58f0e970798c
silenthand is a skill published in the GitHub repository edosulai/silenthand-cua (0 stars, last pushed 10d ago), licensed MIT. It adds 70 tokens to every session and 4,921 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cua-driver
Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive, automate…
scarf-template-author
Scaffold a new Scarf project OR enrich an existing one after a Scarf "Upgrade Project" — dashboard, optional configuration schema, optional cron job, AGENTS.md, and (via the scarf-miniapp-author skill) a starter mini-app — from a short conversational interview. Output is immediately usable locally and cleanly…
scarf-miniapp-author
Author a Scarf mini-app — a small sandboxed web surface (HTML/CSS/JS) that renders inside a project's cockpit and talks to the bound Hermes session + project data through the versioned window.scarf bridge. Use to build a bespoke panel (a task board, an approval queue, a chart, a data table) for a project.
macos-harness
Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…
host-computer-use
Beta desktop control through the connected A0 CLI host. Use for the user's host/local computer screenshots, screen inspection, menus, native app UI, OS-level clicking, scrolling, typing, or checking computeruseremote status. Use instead of linux-desktop for host/local machine control. Do not use for ordinary browser…
computer-basics
How this bot uses its pinned Orgo cloud computer (opt-in load).