room-computer

room-computer is a skill for Claude Code from iammrduncan/fxbot. It costs 27 tokens per session (382 once invoked), scanned A, original, Apache-2.0.

How to share a chat room's computer with the room's other bots. Use when the room has a computer.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Install with agentmods
npx agentmods add skills/iammrduncan/fxbot/room-computer
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 iammrduncan/fxbot --skill room-computer
Clone the repo
git clone --depth 1 https://github.com/iammrduncan/fxbot

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 room-computer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/iammrduncan/fxbot/room-computer"><img src="https://agentmods.dev/badge/skills/iammrduncan/fxbot/room-computer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 382 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 $0.00027 $0.00382
Opus 5.5 $0.00011 $0.00153
Sonnet 5.5 $0.00005 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured today against content hash bbff086388c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

room-computer 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.

plugins/chat-rooms-computer/skills/room-computer/SKILL.md · 39 lines

What it actually says

Sharing a room's computer

The room's computer is one machine for every bot in the room, used in turns. During your turn in the room it's yours: your computer tools reach it, not your own. Your own computer is for your own chats.

Look first

Someone may have changed it since your last turn. Before you act:

  • take a screenshot with computer_desktop
  • run agent-browser snapshot -i or agent-desktop snapshot for what you'll work in
  • read the terminal with computer_terminal and no text

The browser is shared, with its sign-ins

  • Start your work in a tab of your own: agent-browser tab new --label <your name> <url>.
  • Come back to it with agent-browser tab <your name>, which brings it to the front, so the screen shows it.
  • Leave the others' tabs open, and don't sign out of anything.

The terminal is everyone's

The terminal, the tmux session main, is the same for every bot and for the owner. Leave it at a prompt when your turn ends. Run a server with setsid through computer_shell, not in the terminal.

Files

/root is shared. Keep your own work in /root/<your name>/, and put what's for the room where you tell the room.

Say what you did

Say in the room what you did on the computer and where, so the next bot can carry on.

Only the owner

For what only the owner can do, such as a sign-in, call computer_ask_owner. The owner tags you when it's done.

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 · 39 lines · 27 tokens per session scan A bbff086388c8

Subscribe to this mod's changes

room-computer is a skill published in the GitHub repository iammrduncan/fxbot (11 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 382 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 2026-11-06.

Related

room-computer compared with skills from other repositories

room-computer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
room-computeriammrduncan/fxbotSkill11todayApache-2.0A27Claude Code
compare-harnessesruvnet/metaharnessSkill738yesterdayMITA66Claude Code
oia-manifestruvnet/metaharnessSkill738yesterdayMITA79Claude Code
create-harnessruvnet/metaharnessSkill738yesterdayMITA89Claude Code
diag-harnessruvnet/metaharnessSkill738yesterdayMITA85Claude Code
example-harnessruvnet/metaharnessSkill738yesterdayMITA90Claude Code
repo-genomeruvnet/metaharnessSkill738yesterdayMITA73Claude Code