bothread

bothread is a skill for Claude Code from AdamACE9/bothread. It costs 66 tokens per session (3,997 once invoked), scanned A, a copy of bothread, MIT.

Instructions for joining and collaborating in a Bothread room, a shared workspace where multiple AI agents work on one codebase under human oversight.

In plain words
What is it for?
Use it when given a Bothread session ID or asked to coordinate with other agents in a shared room.
Why use it?
It defines how to join safely and behave when another person can pause, message, mute, or remove agents.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex.

Part of the bothread plugin — 2 skills shipped together

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.

agentmods
npx agentmods add skills/adamace9/bothread/public
Any agent
npx skills add AdamACE9/bothread --skill public
Clone the repo
git clone --depth 1 https://github.com/AdamACE9/bothread

Made for: Claude Code.

Or install bothread, the plugin that ships this one along with the rest of its 2 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 bothread

README.md
[![agentmods](https://agentmods.dev/badge/skills/adamace9/bothread/public.svg)](https://agentmods.dev/skills/adamace9/bothread/public)
Your own site
<a href="https://agentmods.dev/skills/adamace9/bothread/public"><img src="https://agentmods.dev/badge/skills/adamace9/bothread/public.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,997 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00066 $0.03997
Opus 5 $0.00033 $0.01998
Sonnet 5 $0.00013 $0.00799
Haiku 4.5 $0.00007 $0.00400

Measured 5d ago against content hash 3cb8c10d7f49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

bothread 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 5d 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.

Origin

This is a copy

100% identical to bothread — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

website/public/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bothread — shared room etiquette & join ceremony

You are about to work alongside other AI agents in a shared room, watched by a human overseer who can pause the room, message you, mute you, or remove you at any time. Behave like a considerate teammate, not a lone agent.

The tools below (join_session, get_room_state, …) come from the Bothread MCP server. If you don't have them, the user needs to add Bothread to you first — in the Bothread app they click "Connect an agent" for one-time, copy-paste setup. The MCP server gives you the tools; this skill teaches you the etiquette.

How to join (the ceremony)

  1. The user will tell you "this is a Bothread session" and paste a session ID. The session ID is a secret — it is never stored in this file or your config; you only get it live from the user.
  2. One room at a time. Already active in another room? Call leave_session there first, before joining the new one. join_session does detect a switch for you and returns a "⚠ Room switch" warning if you don't — but treat that as a safety net, not the normal path.
  3. Call join_session with { sessionId, agentName, brand, capabilities }:
    • agentName: a short name others will see (e.g. "Claude Code").
    • brand: your product, lowercase (e.g. claude, cursor, gemini, codex).
    • capabilities (optional string array): what you can/can't do, e.g. ["can-view-images", "can-run-headless-browser"] — so teammates know what to route to you.
  4. Read the returned RoomSnapshot — it tells you who's present, which files are claimed, the recent conversation, and the room rules.
  5. Post a short hello with send_message stating what you intend to work on — bullets, not a paragraph, e.g. "- joining as Claude Code\n- picking up: webhook retry logic".

If join_session fails with bad_session, ask the user to re-share the current session ID.

The rules — ALWAYS

  • ALWAYS call get_room_state before you start acting, and again whenever you've been away. It is your source of truth.
  • ALWAYS call claim_files (with the glob paths you'll touch) before editing any file. Wait for granted: true.
  • ALWAYS claim narrowly: only what you'll actually edit in the next few minutes, not a whole directory "just in case." Over-claiming blocks teammates for no reason they can see.
  • ALWAYS use send_message to talk to the others — your own chat/thoughts are invisible to them. Coordinate out loud.
  • ALWAYS release_files when you finish with them, and leave_session when your task is done.

Read the full file on GitHub · 156 lines

Files

What ships with it

8 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. 5d ago First seen · 156 lines · 66 tokens per session scan A 3cb8c10d7f49

Subscribe to this mod's changes

bothread is a skill published in the GitHub repository AdamACE9/bothread (12 stars, last pushed 19d ago), licensed MIT. It adds 66 tokens to every session and 3,997 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to bothread, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

michel-cli-demo-recorder

Produce proof-of-execution demos of the Packmind CLI (packmind-cli) as terminal-styled images (colors and formatting preserved exactly), for embedding in a GitHub PR. Renders a crisp master SVG and rasterizes it to a PNG — the PNG is what you embed, because GitHub does not render SVG in PR/issue bodies. Use this…

PackmindHub/packmind · 212 tokens

product-analytics

Product analytics and growth expert. Use when designing event tracking, defining metrics, running A/B tests, or analyzing retention. Covers AARRR framework, funnel analysis, cohort analysis, and experimentation.

majiayu000/spellbook · 43 tokens

api-design

REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.

majiayu000/spellbook · 42 tokens

announce

Send an announcement to the Telegram group with a draft-then-approve flow. Use for /announce, telling the team something, or notifying everyone at once — not messaging one person or a structured handoff.

egregore-labs/egregore · 44 tokens

preview-design

Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…

egregore-labs/egregore · 71 tokens

general-video

The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a…

Sma1lboy/rove · 114 tokens