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 agentmods add skills/maddada/ghostex/ghostex-clinpx skills add maddada/Ghostex --skill ghostex-cligit clone --depth 1 https://github.com/maddada/GhostexWhat 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 | $0.00135 | $0.00678 |
| Opus 5 | $0.00068 | $0.00339 |
| Sonnet 5 | $0.00027 | $0.00136 |
| Haiku 4.5 | $0.00014 | $0.00068 |
Grade A, and why
ghostex-cli 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 2d 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-cli
Use Ghostex's CLI help as the source of truth instead of relying on remembered command names or flags.
Core Workflow
-
Read the current command catalog:
ghostex --help -
Read focused help when the catalog points to it:
ghostex automations --help ghostex quick-actions --help ghostex browser --help ghostex server --help -
Inspect current state before choosing a target. Prefer JSON where offered:
ghostex sessions --json ghostex state -
Act on an exact project, session, group, automation, or run id. Prefer ids from JSON output over titles, aliases, or whichever project is focused.
-
Re-read the relevant state or use the command's assertion/wait operation to verify the requested result.
Routing
Everyday Ghostex work — sessions, orchestration, automations, quick actions, chat queues, prompt history, server, diagnostics — is covered by the CLI help above. Route to a specialized skill only when its domain applies:
- Use
$ghostex-embedded-browser-usefor browser panes inside Ghostex. - Use
$ghostex-browser-usefor supported external browser page content. - Use
$ghostex-computer-usefor native desktop application control. - Use
$ghostex-manage-beadsfor Project Board bead workflows through the machine-installedbdCLI. - Use
$ghostex-fable-56-orchestrationfor the Fable-planned, Codex-implemented, Fable-verified multi-pane pipeline. - Use
$ghostex-auto-rename-sessionwhen asked to generate a session title. - Use
$ghostex-move-codex-sessionto fork a Codex session into another folder.
Keep using this skill's inspect, act, and verify loop alongside the specialized workflow.
Safety
- Do not guess a command, selector, flag, or JSON shape when current help can provide it.
- Inspect exact targets before delete, kill, archive, replacement, or bulk operations.
- Use
--token-stdinfor temporary remote tokens; do not put secrets in argv. - Do not use raw zmx or tmux commands when Ghostex exposes the operation.
- Do not treat a successful process exit as verification when state can be checked directly.
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.
- 2d ago First seen · 80 lines · 135 tokens per session scan A b6f6dead1222
ghostex-cli is a skill published in the GitHub repository maddada/Ghostex (714 stars, last pushed 2d ago), licensed MIT. It adds 135 tokens to every session and 678 once invoked, about $0.0007 per session on Opus 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
kanban-code
Inspect cards, delegate work to subagents, orchestrate Claude sessions, and chat with other agents over Kanban Code's channels. Use whenever the user mentions Kanban Code, asks you to spawn or fork a subagent, asks you to coordinate with another running Claude, or is working inside a card's tmux session and wants to…
setup-okf-matt-skills
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
project-spine
Use when the user mentions AGENTS.md, CLAUDE.md, copilot-instructions, Cursor rules, project brief, context for coding agents, agency kickoff, onboarding a new project, or asks "how do I set up Project Spine". This is the orientation skill — reach for it FIRST when the user's intent involves Project Spine, then chain…
03-architect
Realize the system architecture — turn architecture-constraints + sprint REQs (+ 02's design contract) into a lean arc42/C4 system.md, MADR ADRs, and per-feature specs with gradeable Verification Contracts, all referencing REQs. Second skill to run Reconcile, first via a context-isolated subagent: challenges…
scrum-master
Agent team role for Scrum Master facilitation, coaching, and servant leadership. Use when the user asks to facilitate scrum events, coach a team on self-management, resolve impediments, run retrospectives, improve team processes, or address scrum anti-patterns. Owns the "how we work" - ensures the team applies scrum…
role-dev
Use when exactly one approved work package (WORK card) should be implemented — including as a DEV subagent in autonomous-loop. Not for scope decisions, reviews, or when no approved card exists.