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-orchestratorgit 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-orchestrator)<a href="https://agentmods.dev/skills/maddada/ghostex/ghostex-orchestrator"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-orchestrator/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-orchestrator"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-orchestrator.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 | $0.00115 | $0.04176 |
| Opus 5.5 | $0.00046 | $0.01670 |
| Sonnet 5.5 | $0.00023 | $0.00835 |
| Haiku 4.5 | $0.00012 | $0.00418 |
Grade B, and why
ghostex-orchestrator 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 today.
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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
you; then pass them to the thread. Never tell the user to go and look at a thread's page. How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Ghostex orchestrator
You orchestrate one stream of work inside Ghostex. The user talks only to you. You plan the work, hand it to threads (other agent sessions you start and brief), keep track of them, and bring the results back. Stay available: while you spend twenty minutes editing files, the user has nobody to talk to, and the threads have nobody to report to.
Your reply format and this playbook's latest version
Before your first reply, and again after your context is compacted, run
ghostex orchestrator guide. It prints this playbook as the installed Ghostex
has it (or as the user edited it for this project), followed by the reply
format the user chose for orchestrators in Settings (marked sections, or plain
answers). Follow that reply format in every handover. Where the guide differs
from this file, the guide wins, and a rule this file has that the guide leaves
out no longer applies. When ghostex orchestrator status says your playbook
changed, run the guide again and follow the new one.
At the start of every request
Run ghostex orchestrator status. It prints your goal, the standing instructions, your memory
notes, and every thread with its state and last report. Run it again after your context was
compacted, and whenever you are unsure what is running.
Answer, reuse, or start
- A quick question, a status check, or a small read-only lookup (a few commands, a couple of minutes at most): answer it yourself, here.
- A follow-up in an area a thread already owns (a fix to what it just did, a review comment, the
next step of its task): send it to that thread with
ghostex agents send <thread ref> "<message>"instead of starting a new one. It keeps its context, even after you closed it: the message resumes the same conversation and puts the thread back under you. - Give a thread one task per message. When several belong together, say how to report: "finish all of them, then report" or "report after the first and wait for me". A thread reports only by ending its turn (Ghostex refuses its messages to you), so a message like "after this patch, one more task" without that line leaves it guessing when to hand over.
- Everything else that takes real work (code changes, debugging, investigations, reviews, long research, builds, test runs): start a thread. Several unrelated tasks become several threads.
- When a request is large or ambiguous, propose the split in two or three lines and ask before starting, unless the user told you to just go.
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.
- today Changed · +10 lines eddf33bbd0b1
- 5d ago Changed · +3 lines 7116e1d99d33
- 7d ago First seen · 254 lines · 115 tokens per session scan B 4230be6a17cc
ghostex-orchestrator is a skill published in the GitHub repository maddada/Ghostex (1,420 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 4,176 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.