agentmods.dev

drive

drive is a skill for Claude Code from cmj0121/baton. It costs 30 tokens per session (937 once invoked), scanned A, original, MIT.

A guide for an outside coding agent to connect to a running baton session and control its group of terminal panels. Baton is a terminal tool that lets an operator manage multiple agents and commands.

In plain words
What is it for?
Connecting to baton, checking whether it is running, listing panels, and sending control commands from an agent outside baton.
Why use it?
It explains how to find the correct baton service and use its control commands without opening the operator's full-screen interface or taking the wrong role.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the baton plugin — 3 skills shipped together

not rated 2repo 3d ago A scan 30 tokens original MIT

Good fit Connecting to baton, checking whether it is running, listing panels, and sending control commands from an agent outside baton.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cmj0121/baton/drive
View source ↗ cmj0121/baton cmj0121.github.io
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 cmj0121/baton --skill drive
Clone the repo
git clone --depth 1 https://github.com/cmj0121/baton

Made for: Claude Code.

Or install baton, the plugin that ships this one along with the rest of its 3 skills.

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 drive

README.md
[![agentmods](https://agentmods.dev/badge/skills/cmj0121/baton/drive/github.svg)](https://agentmods.dev/skills/cmj0121/baton/drive)
Your own site
<a href="https://agentmods.dev/skills/cmj0121/baton/drive"><img src="https://agentmods.dev/badge/skills/cmj0121/baton/drive/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 drive

Your own site · 80×15
<a href="https://agentmods.dev/skills/cmj0121/baton/drive"><img src="https://agentmods.dev/badge/skills/cmj0121/baton/drive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 937 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 $0.00030 $0.00937
Opus 5.5 $0.00012 $0.00375
Sonnet 5.5 $0.00006 $0.00187
Haiku 4.5 $0.00003 $0.00094

Measured 8d ago against content hash 702e1fe9631a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

drive 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 8d 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.

agentplugin/skills/drive/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Driving baton from outside

This skill is for an agent the operator runs in their own terminal, outside any baton panel, and asks to work the fleet for them.

If BATON_PANEL_ID is set and BATON_ROLE is not conductor, you are a worker inside baton: do not drive the fleet from here — keep to your task and the worker's skills, score and peers.

If BATON_ROLE is conductor, you are the conductor: read conduct, not this.

Connecting

baton is one daemon per user by default, holding the fleet, and a cockpit the human watches it through. You reach the daemon over its control socket:

  • The default socket is $XDG_RUNTIME_DIR/baton/baton.sock, or ~/.baton/baton.sock when that variable is unset. BATON_SOCK points at a different daemon's socket instead.
  • baton ctl list is the check. It prints the fleet as JSON; "is the server running?" means no daemon answers on that socket.
  • Do not start one yourself: plain baton opens the cockpit, a full-screen terminal UI meant for the human. Ask them to start it.

Every baton ctl command connects, acts, and exits. Run them through your shell; baton ctl --help and baton ctl <verb> --help print the exact forms.

MCP, if you want tools

Nothing is wired for you. To get structured tools instead of shelling out, the operator can register baton's MCP server once:

claude mcp add baton -- baton mcp

That serves the full fleet table — the same one the conductor gets — over the same socket. The conduct skill names every tool in it and when to use each. Without MCP, baton ctl covers the same ground.

Your role: unscoped

From outside, you connect with no role and no panel: the cockpit's own, unscoped role. The conductor is fenced — it may not drain the queue, sweep worktrees, switch peers, or act on its own panel. You are not: apart from the fleet ceiling of 64, the conductor-only memory corrections and the rate cap on baton ctl score submit, nothing in the server stops you, so the judgment is yours.

Read the full file on GitHub · 79 lines

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. 8d ago First seen · 79 lines · 30 tokens per session scan A 702e1fe9631a

Subscribe to this mod's changes

drive is a skill published in the GitHub repository cmj0121/baton (2 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 937 once invoked, about $0.0001 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 2026-10-29.

Building agentsClaude CodeGoai-agentsbubbleteaclideveloper-tools
Related

drive compared with skills from other repositories

drive next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
drivecmj0121/batonSkill23d agoMITA30Claude Code
gh-skillcli/cliSkill47ktodayMITA41Claude Code, Codex
printing-press-amendmvanhorn/cli-printing-pressSkill4.9kyesterdayMITA222Claude Code
printing-press-importmvanhorn/cli-printing-pressSkill4.9kyesterdayMITA104Claude Code
octo-driveMininglamp-OSS/octo-cliSkill922yesterdayApache-2.0A55Claude Code, Codex
octo-mailMininglamp-OSS/octo-cliSkill922yesterdayApache-2.0A32Claude Code, Codex
octo-docsMininglamp-OSS/octo-cliSkill922yesterdayApache-2.0A101Claude Code, Codex