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-spaceogit 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-spaceo)<a href="https://agentmods.dev/skills/maddada/ghostex/ghostex-spaceo"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-spaceo/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-spaceo"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-spaceo.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 | $0.00078 | $0.01331 |
| Opus 5.5 | $0.00031 | $0.00532 |
| Sonnet 5.5 | $0.00016 | $0.00266 |
| Haiku 4.5 | $0.00008 | $0.00133 |
Grade A, and why
ghostex-spaceo 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 23d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ghostex-spaceo
Use this skill when a task needs a native Mac app (or a page in a Chromium
browser) driven out of the user's way. SpaceO opens the app on a virtual
display the user cannot see, so you click, type and take screenshots there
while the user keeps working on their own screen. Use $ghostex-computer-use
instead when the user wants an app driven on their own screen.
Use the spaceo CLI. Ghostex installs SpaceO without registering its MCP
server; if your client already lists spaceo_* MCP tools (the user set them up
themselves), they drive the same daemon and you may use them instead.
Requirements
- An Apple Silicon Mac with macOS 14 or later. SpaceO does not run on Intel Macs, Windows or Linux.
- SpaceO must be installed. Ghostex installs it from Settings > Integrations,
which runs SpaceO's official installer and keeps its daemon running in the
background (the
com.spaceo.daemonLaunchAgent). - Accessibility and Screen Recording must be on for the app SpaceO names. Settings > Integrations shows which app that is and opens the right pane.
Check the machine before acting (read-only, nothing is changed):
command -v spaceo || ls ~/.local/bin/spaceo
spaceo daemon wait --timeout 2 --json # daemon.accessibilityGranted, daemon.screenRecordingGranted
spaceo doctor # full report; every MISS line names its fix
If spaceo is not on PATH, call ~/.local/bin/spaceo. If no daemon answers
and the LaunchAgent is installed, restart it with
launchctl kickstart -k gui/$(id -u)/com.spaceo.daemon. If permissions are
missing, stop and tell the user to turn them on in Settings > Integrations.
Sessions and the lease
Every task runs in a session, and every session-scoped command needs the session's controller lease. Each of your shell calls starts fresh, so save the lease in a private file once and source it in every later call:
env_file="${TMPDIR:-/tmp}/spaceo-<task-name>.env"
spaceo session create --session <task-name> --controller-ttl 1800 --export > "$env_file"
. "$env_file" && spaceo run TextEdit
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.
- 23d ago First seen · 102 lines · 78 tokens per session scan A c1ae2264ea93
ghostex-spaceo is a skill published in the GitHub repository maddada/Ghostex (1,420 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,331 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.
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…