batonbot
Interact with BatonBot, the visual AI agent workflow orchestrator.
Sorting a stream of records into a picture
What it does
> Important: Always cd to the project root before running npm commands. > Docker is also supported (docker compose up --build -d) — see the README's Docker Deployment section. For local dev, run the server directly via npm.
Use when Michael asks about: starting or stopping the BatonBot server, managing projects or tasks, creating pipelines, assigning agents…
You don’t need to name it. Ask for the job in your own words — your AI loads the skill when the request matches.
What it can touch
Includes 26 scripts
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: app.js, batonbot.js, modules/agents/baton-code-thinking.js, modules/agents/baton-code.js….
Asks for an API key or token
You will need an account with the service it talks to, and your own key. Keep keys in your settings or environment, never in a chat.
How we know
The SKILL.md mentions an API key or access token.
Uses terminal commands
It shows your AI commands to run. In a coding agent that means your terminal; in a chat app it usually can’t.
How we know
The SKILL.md contains shell code blocks.
Its code sends data over the internet
A script in it uploads or posts data. That is normal for a skill that talks to a service — check that the address is the service you expect.
How we know
README.md line 342: “curl -X POST http://localhost:3000/api/projects/proj_123/ingest -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" -d…”. Read 2026-10-05, commit f2cd58e.
README.md, line 342 ↗Adds a connector (MCP server)
It sets up a separate program your AI can call. That program is not covered by this check.
How we know
An MCP configuration or "mcp add" command in its files. Read 2026-10-05, commit f2cd58e.
3 smaller things worth knowing
Removes macOS download protection from a file; Posts to a Discord or Telegram bot. Usually legitimate — listed so nothing is hidden.
How we know
Removes macOS download protection from a file — README.md line 101; Posts to a Discord or Telegram bot — batonbot.js line 1472; Removes macOS download protection from a file — scripts/build-portable/build-mac.js line 165. Read 2026-10-05, commit f2cd58e.
README.md, line 101 ↗batonbot.js, line 1472 ↗scripts/build-portable/build-mac.js, line 165 ↗No serious risk pattern found
Launch7’s automated check read all 45 text files in this skill and matched none of its serious risk patterns. This is not a guarantee: a check like this can miss new or disguised tricks, and the author can change the files after the check.
How we know
Read 2026-10-05, commit f2cd58e by pipeline/trust/analyze.py — 40+ patterns for hidden text, prompt injection, downloads that run, credential access and more. It reads; it never runs the skill.
Recently maintained
Its repository has had changes recently.
How we know
Last push to mdoty4/batonbot: 2026-08-10 (56 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 26 scripts beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end