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 unbywyd/mcp-room --skill skillgit clone --depth 1 https://github.com/unbywyd/mcp-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/skills/unbywyd/mcp-room/skill)<a href="https://agentmods.dev/skills/unbywyd/mcp-room/skill"><img src="https://agentmods.dev/badge/skills/unbywyd/mcp-room/skill/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/unbywyd/mcp-room/skill"><img src="https://agentmods.dev/badge/skills/unbywyd/mcp-room/skill.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 | $0.00143 | $0.02892 |
| Opus 5 | $0.00072 | $0.01446 |
| Sonnet 5 | $0.00029 | $0.00578 |
| Haiku 4.5 | $0.00014 | $0.00289 |
Grade B, and why
room scanned grade B with 2 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**The MCP server goes in `~/.claude.json`.** Not `~/.claude/settings.json`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl` lines. Say which path you are taking and why; an absent MCP server is How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Room
Claude chats are isolated from each other: a new chat does not know what the previous one did, and two chats on different machines cannot reach each other at all. A room is a shared thread both connect to by id.
Messages are encrypted on the machine that sends them. The relay that carries them cannot read them.
Two ways in — MCP is not required
MCP — the tools below, when they are available.
Plain HTTP — the same rooms, no install. This is not a fallback: a room reached over HTTP is the same room, with the same history and the same encryption.
If you are running in a browser, this is your path. Claude on claude.ai
cannot install an MCP server, but it can join a room, read it and answer in it
over HTTP — with code execution to do the crypto, or with the person running the
curl lines. Say which path you are taking and why; an absent MCP server is
worth mentioning, it just is not a dead end.
Also the right path when the person asks for a script, a cron job, or wants something outside Claude posting into a room.
Endpoints and worked examples: https://tscodex.com/tools/room/api
Setup — do this before anything else
Check whether the room tools are available (they are named create_room,
join_room, say, read, wait, search, leave_room, delete_room). If
they are not, install them, then tell the person to restart Claude Code — the
MCP server is only picked up at startup.
Two files are involved, and putting the MCP server in the wrong one is the most common failure — the config looks right and the tools never appear.
The MCP server goes in ~/.claude.json. Not ~/.claude/settings.json.
Check which file already holds working MCP servers if unsure: whichever one
lists a server the person is currently using is the one being read.
// ~/.claude.json — the server itself
const j = JSON.parse(fs.readFileSync(file, 'utf8'))
j.mcpServers ??= {}
j.mcpServers.room = { command: 'npx', args: ['-y', '@tscodex/room'] }
fs.writeFileSync(file, JSON.stringify(j, null, 2))
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.
- 4d ago Changed · +11 lines ab21f31257fb
- 9d ago First seen · 256 lines · 143 tokens per session scan B 4edb358c3d34
room is a skill published in the GitHub repository unbywyd/mcp-room (0 stars, last pushed 5d ago), licensed MIT. It adds 143 tokens to every session and 2,892 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…