Ghostex is a developer workspace for running and supervising multiple AI coding agents, with separate chats, command-line views, and persistent sessions in a Rust-based desktop shell. Developers use it to switch between agents, review work, preview pages, and continue sessions from mobile devices.
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 maddada/Ghostex --skill ghostex-computer-usegit clone --depth 1 https://github.com/maddada/GhostexWrote 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/maddada/ghostex/ghostex-computer-use)<a href="https://agentmods.dev/skills/maddada/ghostex/ghostex-computer-use"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-computer-use/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/maddada/ghostex/ghostex-computer-use"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-computer-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 45 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00058 | $0.01467 |
| Opus 5.5 | $0.00023 | $0.00587 |
| Sonnet 5.5 | $0.00012 | $0.00293 |
| Haiku 4.5 | $0.00006 | $0.00147 |
Grade C, and why
ghostex-computer-use 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 18d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- CDXC:CuaPermissions 2026-05-29-12:21: State checks must be read-only. The default Trycua permission check can ask macOS to show missing-grant prompts, so the Ghostex wrapper uses prompt:false and only sends users to How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ghostex-computer-use
Use this skill when a task needs native macOS app automation through Ghostex
Desktop Control. This skill is a wrapper around $cua-driver: read that skill
first (below), and issue operations through the cua-driver CLI.
Read the cua-driver skill first
Before the first cua-driver call, read Trycua's cua-driver skill: it is the
source of truth for the installed driver's tools, schemas, safety rules and
platform notes, and this skill only adds Ghostex's guidance on top. Load
$cua-driver if your agent offers it; otherwise read its SKILL.md and the
reference files it links:
cat "$(cua-driver skills path)/SKILL.md"
From WSL, ask the Windows side for the path and translate it:
cat "$(wslpath -u "$(powershell.exe -NoProfile -Command 'cua-driver skills path' | tr -d '\r')")/SKILL.md"
If the skill is missing, install it with cua-driver skills install (through
powershell.exe from WSL), or from Settings > Integrations.
Use the CLI, not MCP. Do not configure, register, or invoke a Trycua MCP server for this workflow.
Route browser work by surface:
- Use
$ghostex-browser-usefor web content in external Chrome, Chromium, Edge, or supported Electron apps through Trycua's typed browser tools. - Use
$ghostex-embedded-browser-usefor browser panes built into Ghostex. - Continue with this skill for native apps, browser chrome, native browser dialogs, or browser engines that do not expose an exact typed page route.
Requirements
- Trycua must be installed. Ghostex installs it from first-launch setup or
Settings > Integrations, where the Fast Computer & Browser Use row runs the
official installer and installs the
$cua-driverskill with it. - Trycua must be available as
cua-driver(see Windows and WSL below). - macOS Accessibility and Screen Recording permissions must be granted for Trycua.
Check the machine state before acting:
which cua-driver
cua-driver status
cua-driver check_permissions '{"prompt":false}'
What ships with it
1 file 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.
- 18d ago Changed · +20 lines 67de3b9f2abf
- 19d ago Changed f90aac7e1aa0
- 24d ago Changed 3d46a97c2167
- 1mo ago Changed · +3 lines 3dd0603b32c5
- 1mo ago First seen · 130 lines · 58 tokens per session scan C fca92a9c12e0
ghostex-computer-use is a skill published in the GitHub repository maddada/Ghostex (1,420 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,467 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…