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 agentmods add instructions/quoroom-ai/room/agents-mdgit clone --depth 1 https://github.com/quoroom-ai/roomWrote 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/instructions/quoroom-ai/room/agents-md)<a href="https://agentmods.dev/instructions/quoroom-ai/room/agents-md"><img src="https://agentmods.dev/badge/instructions/quoroom-ai/room/agents-md.svg" alt="Measured on agentmods" 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 | $0.00408 | $0.00408 |
| Opus 5 | $0.00204 | $0.00204 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
room AGENTS.md 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.
What it actually says
BEGIN VASILY GLOBAL SHORTCUTS
Global Shortcut Commands (From /cloud/CLAUDE.md)
These shortcuts are mandatory and should be interpreted automatically when the user types them.
Keyboard Layout Recovery
If a short command is typed in Cyrillic by mistake, convert to English QWERTY before interpreting.
Common mapping example: с -> c, св -> cd, ск -> cr (layout-dependent).
c = Commit And Push (No Build)
- In
roomrepo:
- Run
npx tsc --noEmit. - Check changed files for missing tests.
- Run
npm test. - If staged files touch
e2e/or Playwright config, run smart E2E flow. - Update docs (including
CLAUDE.md) when needed. - Check git status.
- Commit with a meaningful message.
- Push:
git push origin main.
- In
cloudrepo: commit and push (no TypeScript/test requirement).
cd = Commit, Push, Build (Full)
- Do everything from
c, then runnpm run build. - If build fails, fix and repeat from git-status step.
cr = Commit, Build, Bump And Tag (Release)
- Do everything from
cd. - Run
npm version patch. - Push tags:
git push origin main --tags. - Release commit message should be one sentence focused on the single most important change.
E2E Rule For room
- For
c/cd: run E2E only whene2e/or Playwright config changed. - For
cr: always run full E2E (npm run test:e2e).
Operator Preference
- Assume approval for non-destructive commands and proceed without asking for confirmation in chat.
END VASILY GLOBAL SHORTCUTS
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.
- 5d ago First seen · 39 lines · 408 tokens per session scan A 396f8874c960
room AGENTS.md is an instructions file published in the GitHub repository quoroom-ai/room (835 stars, last pushed 4mo ago), licensed MIT. It adds 408 tokens to every session, about $0.0020 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 2026-08-30.
Other instructions, from other repositories
ECC copilot-instructions.md
Copilot instructions for affaan-m/ECC, covering ecc for github copilot, core workflow, prompt defense baseline, coding standards and immutability.
open-swe AGENTS.md
AGENTS.md instructions for langchain-ai/open-swe, covering agents.md, project, commands, architecture and entrypoints.
open-swe CLAUDE.md
Claude Code instructions for langchain-ai/open-swe, a project described as: An Open-Source Asynchronous Coding Agent.
MiniAgent AGENTS.md
Instructions for ZhuLinsen/MiniAgent, covering agents.md — miniagent 项目指南, 项目定位, 核心原则, 1. 极简即力量 and 2. 透明可控.
earheart AGENTS.md
AGENTS.md instructions for cleanunicorn/earheart, covering agents.md, golden rules, the github flow, step by step, 1. start from an up-to-date main and 2. create a branch.
ai-git-commiter CLAUDE.md
Instructions for zdt1013/ai-git-commiter, covering ai git commiter, 项目结构, 技术栈, 常用命令 and 安装依赖.