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-embedded-browser-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-embedded-browser-use)<a href="https://agentmods.dev/skills/maddada/ghostex/ghostex-embedded-browser-use"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-embedded-browser-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-embedded-browser-use"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-embedded-browser-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00089 | $0.00763 |
| Opus 5.5 | $0.00036 | $0.00305 |
| Sonnet 5.5 | $0.00018 | $0.00153 |
| Haiku 4.5 | $0.00009 | $0.00076 |
Grade A, and why
ghostex-embedded-browser-use 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 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.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ghostex-embedded-browser-use
Use Ghostex's CEF DevTools bridge for pages rendered inside Ghostex. This route does not require a second browser automation runtime.
Enter through the ghostex CLI, not a configured MCP integration. Do not add a
persistent mcp_servers.ghostex-browser entry. The temporary stdio bridge
speaks MCP internally because that is the embedded page-control protocol, but
launch it only through ghostex browser mcp for the current task.
Requirements
- Ghostex must be running before the CLI-launched bridge can attach to CEF.
- A pane can be created or reused with
ghostex browser open <url>. - The Ghostex CLI is bundled with the desktop app and linked on app startup.
- Install this skill with
ghostex browser install-skillwhen needed.
CLI transport
Launch the bridge directly from the CLI for the current task:
ghostex browser mcp
If Ghostex uses a non-default CEF remote-debugging port, pass it explicitly:
ghostex browser mcp --port 9333
The same value can be provided as GHOSTEX_CEF_REMOTE_DEBUGGING_PORT.
Canonical loop
- Open or reuse a suitable pane with
ghostex browser open <url>. - Call
ghostex_list_pagesand select the intended pane withghostex_select_pagewhen multiple pages exist. - Read
ghostex_console_logsbefore and after interactions when debugging. - Call
ghostex_snapshotand choose stable@eelement refs. - Perform one action with
ghostex_click,ghostex_fill,ghostex_press_key, orghostex_navigate. - Re-run
ghostex_snapshotafter navigation or a major DOM change. Verify the expected page state before continuing. - Use
ghostex_evaluatefor focused inspection andghostex_screenshotwhen visual evidence matters.
Opening panes
ghostex browser open <url>defaults to the agent process cwd as the project path and reuses a same-origin pane in that project.- Pass
--project-path "$PWD"or--project-id <id>when the task belongs to a specific Ghostex project or worktree. - Keep the returned browser session id and the MCP page id from
ghostex_list_pages; reuse them instead of opening duplicate panes. - Use
--reuse exactfor exact-URL reuse, or--newonly when a separate pane is intentional.
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.
- 1mo ago First seen · 80 lines · 89 tokens per session scan A 1dfa4ba587b2
ghostex-embedded-browser-use is a skill published in the GitHub repository maddada/Ghostex (1,420 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 763 once invoked, about $0.0004 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 2026-08-30.
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…