ghostex-help

ghostex-help is a skill for Claude Code from maddada/Ghostex. It costs 125 tokens per session (1,001 once invoked), scanned A, original, MIT.

An in-app help skill for Ghostex, an agent workspace. It answers questions about Ghostex features, settings, views, buttons, and shortcuts using the installed app guide.

In plain words
What is it for?
Use it to explain how Ghostex works, locate controls, answer how-to questions, and change settings when the user asks.
Why use it?
It avoids relying on outdated or unrelated instructions by checking the guide and live settings available in the current app.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: $skill-name invocation.

Good fit Use it to explain how Ghostex works, locate controls, answer how-to questions, and change settings when the user asks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/maddada/ghostex/ghostex-help
Install

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.

Any agent
npx skills add maddada/Ghostex --skill ghostex-help
Clone the repo
git clone --depth 1 https://github.com/maddada/Ghostex

Made for: Claude Code.

Wrote 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.

agentmods badge for ghostex-help

README.md
[![agentmods](https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-help/github.svg)](https://agentmods.dev/skills/maddada/ghostex/ghostex-help)
Your own site
<a href="https://agentmods.dev/skills/maddada/ghostex/ghostex-help"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-help/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.

agentmods 80×15 button for ghostex-help

Your own site · 80×15
<a href="https://agentmods.dev/skills/maddada/ghostex/ghostex-help"><img src="https://agentmods.dev/badge/skills/maddada/ghostex/ghostex-help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,001 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00125 $0.01001
Opus 5 $0.00063 $0.00500
Sonnet 5 $0.00025 $0.00200
Haiku 4.5 $0.00013 $0.00100

Measured today against content hash 0eaca8080c4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ghostex-help 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 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.

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.

skills/ghostex-help/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ghostex-help

You are the in-app helper for Ghostex, the agent workspace the user is running right now. Answer from the built-in guide and the live settings catalog, never from memory of other terminals or IDEs, and make the change for the user when they ask for one.

Core Workflow

  1. Read the guide before answering anything about the app. Start with the overview, then the chapter that covers the question:

    ghostex guide             # what Ghostex is, its views, and where things live
    ghostex guide features    # every feature: views, sidebar, sessions, chat, agents, remote, board
    ghostex guide settings    # every setting: key, type, allowed values, default, what it does
    ghostex guide hotkeys     # every shortcut and its default binding
    

    The guide is printed by the installed ghostex binary, so it always matches the app version on this machine. Prefer it over the copies in this skill's references/ folder when both are available.

  2. For a "what does X do" or "how do I" question, answer in a few sentences using the guide's wording for view, button, and setting names, and tell the user exactly where to click or which shortcut to press. If the answer is a setting, name it and offer to change it.

  3. For a "change X for me" request, find the setting first:

    ghostex settings list --json --writable   # keys, current values, types, options
    ghostex settings get <key>                 # one setting with its description
    

    Then apply it and read the result back:

    ghostex settings set <key> <value>
    ghostex settings reset <key>
    

    set sends the change through the running desktop app, so it is applied exactly like a save in the Settings modal and the command prints the old and new value once the app has written it. Report that line to the user.

  4. When a row is not agent-writable (accounts, remote pairing, structured values such as hotkeys and tag lists, or rows that are only buttons in the UI), do not try to edit files or JSON. Open the right Settings page with the row already searched and tell the user what to click:

Read the full file on GitHub · 92 lines

Files

What ships with it

5 files 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.

Changes

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.

  1. today First seen · 92 lines · 125 tokens per session scan A 0eaca8080c4e

Subscribe to this mod's changes

ghostex-help is a skill published in the GitHub repository maddada/Ghostex (770 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 1,001 once invoked, about $0.0006 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 2026-09-10.

Related

Other skills, from other repositories

live-tutorial

Create an annotated MP4 tutorial from a workflow demonstrated in the owner's actual application. Use when asked for a tutorial video, not merely to watch an action live.

leon-ai/leon · 36 tokens

ArXiv

Search and retrieve arXiv academic papers by topic, category, or paper ID — with AlphaXiv-enriched AI-generated overviews. Uses arXiv Atom API across cs.AI/cs.LG/cs.CL/cs.CR/cs.MA/cs.SE/cs.IR. Three workflows: Latest, Search, Paper. USE WHEN arxiv, papers, latest papers, research papers, recent ML papers, paper…

danielmiessler/LifeOS · 123 tokens

Teach

Interactive voice-narrated tutorial on whatever the current conversation is about — teaches the topic beat by beat with ASCII diagrams in the terminal while speaking the actual lesson content aloud, asking one question per beat and quizzing until the ideas land. USE WHEN teach me, /teach-me, tutorial, teach me this…

danielmiessler/LifeOS · 126 tokens

read-book

When you want to read and extract structured notes from a book — PDF, EPUB, MOBI, markdown, .txt, pasted text, or URL to a public-domain work. Reads in chunks (by chapter when a TOC exists, by 50-page blocks otherwise), extracts per-chapter TL;DR + key concepts + quotes + action items + frameworks, and offers to…

coreyhaines31/makerskills · 192 tokens

subscription-setup

A setup workflow for creating recurring medical-learning subscriptions after a doctor’s profile has been registered.

TencentCloud/Octop · 80 tokens

style-skill-creator

A writing tool for creating instructions that teach an AI assistant to follow a particular author's style.

bam-bam-2/solo-skills · 0 tokens