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-manage-beadsgit 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-manage-beads)<a href="https://agentmods.dev/skills/maddada/ghostex/ghostex-manage-beads"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-manage-beads/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-manage-beads"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-manage-beads.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 | $0.00098 | $0.01974 |
| Opus 5.5 | $0.00039 | $0.00790 |
| Sonnet 5.5 | $0.00020 | $0.00395 |
| Haiku 4.5 | $0.00010 | $0.00197 |
Grade A, and why
ghostex-manage-beads 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 11d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ghostex-manage-beads
Use this skill when a user asks you to work a project board bead ("tackle bead 12345"), to manage board beads, create or update review tasks, move work through bead statuses, add bead comments, or link a session to a card.
Requirements
- Run bead commands from the repository root so Beads finds the project database
and
.beadsJSONL export. - Use the normal
bdCLI installed in the environment running the project— macOS, Linux, or the selected WSL distribution. - Prefer
bd --helpandbd <command> --helpas the source of truth for the installed Beads version. - Inspect nearby beads before creating a new one so title, labels, status, and external-ref style match the project.
- If the project has no Beads workspace yet (no
.beadsfolder, orbdsays no beads database was found), stop and ask the user whether they want Beads set up in this project. Runbd init, or anything else that creates.beadsfiles, only after they say yes.
Working A Bead: Link This Session First
The moment you are asked to work a bead, put the session you are running in on its card:
gx board associate <bead-id>
That is the whole command. It takes no session id: Ghostex reads the session you are running in from the environment it exports into every pane, and the card starts showing this conversation as the one working it — the same link the board's own "Start work" button writes.
- Do this even though nobody asked you to. A card whose work is invisible is the normal failure: only work dispatched from the card links itself, so an agent asked by hand has to say so.
- It creates nothing. No session, no worker, no duplicate. Running it twice is safe; run it again after a fork or restore so the card follows the session that is really working.
- Pass
--session-id <alias|id|title>to link a different session, and--project-id <id>only when the same bead id exists on more than one board. gx board start-work <bead-id>is a different command with a different job: it dispatches a card to a fresh worker session. Never run it for a bead you are working yourself — that puts a second agent on your card.
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.
- 11d ago Changed ae3104217178
- 18d ago Changed · +2 lines 7de029f71bd6
- 24d ago Changed · +4 lines 0ea3ed8b89c6
- 1mo ago Changed · +7 lines f7941b1e7572
- 1mo ago Changed · +3 lines 6af2381a0066
- 1mo ago First seen · 176 lines · 98 tokens per session scan A 5b41388eee9e
ghostex-manage-beads is a skill published in the GitHub repository maddada/Ghostex (1,420 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 1,974 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
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…