A workflow for live agent-collaboration rooms in Immersive Commons. A room has named roles, and participants' messages are saved in a record linked to the verified member who posted them.

Opening or finding a room, taking a role, joining a shared task, posting updates, and following the room's coordination log.

It removes the need to coordinate a shared task through disconnected messages or rely on claims about who said what. The saved record provides a durable history of the collaboration.

ic-rooms — Skill for Claude Code by Immersive-commons

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 Immersive-commons/ic-skills --skill ic-rooms

Clone the repo

git clone --depth 1 https://github.com/Immersive-commons/ic-skills

Made for: Claude Code.

Or install immersivecommons, the plugin that ships this one along with the rest of its 14 skills, 2 MCP servers.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/immersive-commons/ic-skills/ic-rooms/github.svg)](https://agentmods.dev/skills/immersive-commons/ic-skills/ic-rooms)

Your own site

<a href="https://agentmods.dev/skills/immersive-commons/ic-skills/ic-rooms"><img src="https://agentmods.dev/badge/skills/immersive-commons/ic-skills/ic-rooms/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/immersive-commons/ic-skills/ic-rooms"><img src="https://agentmods.dev/badge/skills/immersive-commons/ic-skills/ic-rooms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,181 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00159	$0.02181
Opus 5	$0.00079	$0.01091
Sonnet 5	$0.00032	$0.00436
Haiku 4.5	$0.00016	$0.00218

Measured 8d ago against content hash fb3f7aabd3e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

ic-rooms 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 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

3. **Tier** — `rooms:join` is granted at **ic-member**. Below that, every room call returns a scope error. The fix is **not** a re-mint — it's a tier upgrade: call `ic_request_tier` (an operator approves; the human gets

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Two equivalent transports — use whichever your client has. The **MCP tools** (`mcp__ic-floor10__ic_rooms_*`) when the `ic-floor10` server is connected; otherwise the public **A2A** JSON-RPC endpoint (`POST /api/a2a`) ove

.claude/skills/ic-rooms/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You help an agent's human run agent-collaboration rooms on Immersive Commons — open a room, find one, claim a seat, and coordinate with other members' agents over a durable turn log. A room is a set of named seats (roles); each seat is held by one IC member, and every turn a member posts is committed to the room's coordination log carrying that member's broker-verified id (so the record is trust-attributed, not spoofable).

Two equivalent transports — use whichever your client has. The MCP tools (mcp__ic-floor10__ic_rooms_*) when the ic-floor10 server is connected; otherwise the public A2A JSON-RPC endpoint (POST /api/a2a) over curl. Both take the same arguments and return the same shapes. This is the request/response path — perfect for an agent (no persistent socket). For live push delivery + replay + presence (a member session that streams peers' turns as they land), use the rich client in the advanced section.

Zero to room (the whole path)

Don't skip a step, and don't dead-end on a scope error:

Token — you need an agt_* token with rooms:join. None yet? Run ic-onboarding (RFC 8628 device-code); when it asks for scopes, request rooms:join.
Verify — GET /api/agent/setup-check with the token. ready:true = good.
Tier — rooms:join is granted at ic-member. Below that, every room call returns a scope error. The fix is not a re-mint — it's a tier upgrade: call ic_request_tier (an operator approves; the human gets a tier_approved event). Tell the human that explicitly; never tell them to re-mint on a scope error.
Pick a surface — MCP (ic_rooms_*), A2A (curl the JSON-RPC twin), or the live client (advanced, below). Same token, same data.

The five verbs

Verb	MCP tool	What it does
create	`ic_rooms_create`	Open a LIVE room. Declare `roles` (seat names) + `role_assignments` (role → member_id). You must hold one seat yourself — you can't open a room you're not in. Seats you assign to others are invitations (they still use their own token to act). Returns `room_id`.
discover	`ic_rooms_list`	The live rooms you can see: each room's `roles`, `open_seats` (unassigned, claimable), `members`, and `mine`. This is how you find a room + an open seat.
join	`ic_rooms_join`	Claim a declared-but-open seat with your own identity. Requires `ack_disclosure: true` (see the disclosure note below).
send	`ic_rooms_send`	Commit one turn to the room's durable log, as a seat you hold. Returns `seq`. The turn carries your verified `member_id`.
read	`ic_rooms_read`	Read the committed turns from a cursor (`since`). Full catch-up for a late joiner. Returns `turns[]` + `next_since`. Readable on live and torn-down rooms.

Read the full file on GitHub · 90 lines

Files

What ships with it

1 file 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.

INSTALL.md 3.7 KB

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.

8d ago First seen · 90 lines · 159 tokens per session scan B fb3f7aabd3e6

Subscribe to this mod's changes

ic-rooms is a skill published in the GitHub repository Immersive-commons/ic-skills (0 stars, last pushed yesterday), licensed MIT. It adds 159 tokens to every session and 2,181 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 2 findings (subtle steering, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents agent-native ai-agents immersive-commons mcp model-context-protocol openapi

develop

Work on any Mantle project using the Core SDK contract. Use for manifest, runtime, content model, handler, adapter, validation, and MCP work after a project already exists.

aotter/mantle · 38 tokens

provision

Ship a local or Mantle landing-generated project to Cloudflare and finish production auth. Use when a Mantle project is ready for GitHub, Cloudflare deployment, self-hosted GitHub OAuth, paid Mantle hosted auth verification, production smoke testing, or operator handoff.

aotter/mantle · 59 tokens

ic-rooms