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 cmj0121/baton --skill peersgit clone --depth 1 https://github.com/cmj0121/batonWrote 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/cmj0121/baton/peers)<a href="https://agentmods.dev/skills/cmj0121/baton/peers"><img src="https://agentmods.dev/badge/skills/cmj0121/baton/peers/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/cmj0121/baton/peers"><img src="https://agentmods.dev/badge/skills/cmj0121/baton/peers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00035 | $0.00940 |
| Opus 5.5 | $0.00014 | $0.00376 |
| Sonnet 5.5 | $0.00007 | $0.00188 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
peers 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.
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.
Peers
Your peers are the other running panels filed directly in your own baton group.
When the operator switches peer interaction on for that group you may list them
(baton_peers), read a peer's recent output (baton_peek), and type one line
into its terminal (baton_tell). It is off by default, set per group, and only
the operator can switch it.
When to reach for them
- You need something a group-mate knows or has made — whether it finished, what it decided, the result of its build. Peek first; often that answers it.
- You split work with a peer and a handoff point arrived: the interface it consumes is ready, or you need it to stay out of a file for a moment.
- A shell or command panel in your group is running the tests or a server you depend on. Read its output instead of starting a second copy.
Not for chatting, status pings, or handing off your own task. A tell is not a dispatch: no task is recorded on the peer and nothing tracks it to completion.
How
- List first.
baton_peersis the only source of ids, and it lists only the panels you may reach right now. Never guess an id. - Peek before you tell. See what the peer is doing. Your line becomes its next prompt — if it is mid-task, it reads your line when it gets there.
- Say it in one self-contained line. An agent peer sees your title and id in front of it, and nothing else of your context. Say what you need and how you will look for the answer.
- Check it landed. The reply means the line was typed and Enter pressed, not that the peer acted on it. Peek again later.
Agent or shell
Check the kind from baton_peers before every tell.
- An agent gets prose: one line, line breaks folded to spaces, control characters refused. Ask; do not command.
- A shell or command panel runs exactly what you type, as a command, with its own permissions. Type only what you would run yourself, and never use a peer to do something you are not allowed to do directly.
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.
- 8d ago First seen · 79 lines · 35 tokens per session scan A 65b4f3ffb4ff
peers is a skill published in the GitHub repository cmj0121/baton (2 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 940 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.
peers compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| peerscmj0121/baton | Skill | 2 | 3d ago | MIT | A | 35 | Claude Code, Codex |
| gh-skillcli/cli | Skill | 47k | today | MIT | A | 41 | Claude Code, Codex |
| printing-press-amendmvanhorn/cli-printing-press | Skill | 4.9k | yesterday | MIT | A | 222 | Claude Code |
| printing-press-importmvanhorn/cli-printing-press | Skill | 4.9k | yesterday | MIT | A | 104 | Claude Code |
| octo-driveMininglamp-OSS/octo-cli | Skill | 922 | yesterday | Apache-2.0 | A | 55 | Claude Code, Codex |
| octo-mailMininglamp-OSS/octo-cli | Skill | 922 | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| octo-docsMininglamp-OSS/octo-cli | Skill | 922 | yesterday | Apache-2.0 | A | 101 | Claude Code, Codex |