agent-room

agent-room is a cursor rule for Cursor from umbecanessa/agent-room-mcp. It costs 71 tokens per session, scanned A, original, MIT.

Rules for coordinating coding work with another agent through Agent Room, a shared chat and message log for coding assistants.

In plain words
What is it for?
Use it to read or send teammate messages, create or join a project room, and wait for a response when another agent is needed.
Why use it?
It reduces conflicts when two agents work in the same project by requiring message checks before shared edits and providing a way to exchange questions and status.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to read or send teammate messages, create or join a project room, and wait for a response when another agent is needed.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/umbecanessa/agent-room-mcp/agent-room
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.

Clone the repo
git clone --depth 1 https://github.com/umbecanessa/agent-room-mcp

Made for: Cursor.

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 agent-room

README.md
[![agentmods](https://agentmods.dev/badge/rules/umbecanessa/agent-room-mcp/agent-room/github.svg)](https://agentmods.dev/rules/umbecanessa/agent-room-mcp/agent-room)
Your own site
<a href="https://agentmods.dev/rules/umbecanessa/agent-room-mcp/agent-room"><img src="https://agentmods.dev/badge/rules/umbecanessa/agent-room-mcp/agent-room/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 agent-room

Your own site · 80×15
<a href="https://agentmods.dev/rules/umbecanessa/agent-room-mcp/agent-room"><img src="https://agentmods.dev/badge/rules/umbecanessa/agent-room-mcp/agent-room.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 This file is loaded in full into every session.
When invoked 71 The same file — it is already loaded in full.
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 $0.00071 $0.00071
Opus 5 $0.00036 $0.00036
Sonnet 5 $0.00014 $0.00014
Haiku 4.5 $0.00007 $0.00007

Measured 8d ago against content hash 3b1b2a735e10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-room 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.

.cursor/rules/agent-room.mdc · 11 lines

What it actually says

Before editing shared/core files, call read_messages.

When the user asks you to help a teammate, or when injected Agent Room messages appear, reply with send_message.

When blocked waiting for a teammate answer, you may call wait_for_messages once (timeout 25s).

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 · 11 lines · 71 tokens per session scan A 3b1b2a735e10

Subscribe to this mod's changes

agent-room is a cursor rule published in the GitHub repository umbecanessa/agent-room-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session, about $0.0004 per session on Opus 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 2026-08-31.