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 sonichi/sutando --skill agent-room-opsgit clone --depth 1 https://github.com/sonichi/sutandoWrote 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/sonichi/sutando/agent-room-ops)<a href="https://agentmods.dev/skills/sonichi/sutando/agent-room-ops"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/agent-room-ops/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/sonichi/sutando/agent-room-ops"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/agent-room-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.05486 |
| Opus 5.5 | $0.00000 | $0.02194 |
| Sonnet 5.5 | $0.00000 | $0.01097 |
| Haiku 4.5 | $0.00000 | $0.00549 |
Grade A, and why
agent-room-ops 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
room-ops — an agent's room-participation capability collection
For an all-room analysis sweep, use the tested window collector and coverage
contract in history-workflow.md. Archive-derived room IDs
and fixed recent limits cannot establish all-room coverage. Fallback text posts
support --strict say ROOM --body-file FILE and require receipt inspection.
DEPRECATED — room ops (
POST <gateway>/v1/room) is being removed. Use the AG2 Space MCP room Actions instead.room_ops.pyis kept only as a fallback for when the MCP is unreachable (or for the gaps listed below) — never the first path.
Use the AG2 Space MCP first
Call room Actions through the existing façade tools only — room.actions.search,
room.actions.describe, room.action.read (zero-effect reads),
room.action.execute (mutations), operation.inspect — plus the fixed
room.list. Availability is per-room and per-actor, so discover before calling.
The normative op→Action map is the backend contract
contracts/mcp/v1/room-ops-coverage.json (explained in
docs/mcp-room-ops-coverage.md).
| room_ops.py verb | MCP call | Action |
|---|---|---|
rooms |
room.list (fixed tool) |
— |
read |
room.action.read |
room.context.read |
members |
room.action.read |
room.members.list |
mention (name → mxid) |
room.action.read |
room.member.resolve, then room.message.send with the mxid in mentions |
say |
room.action.execute |
room.message.send |
react / unreact |
room.action.execute |
room.message.react / room.message.unreact |
send (upload) |
room.action.execute |
room.media.upload |
fetch |
room.action.execute |
room.media.link (an expiring viewer link, not a local file) |
events emit |
room.action.execute |
room.event.send |
| state read / write | room.action.read / room.action.execute |
room.state.read / room.state.write |
Gotchas
- Mutations need an
operation_id. What to do onACTION_OUTCOME_UNKNOWNdepends on the Action:- Built-in
room.*Actions: retry with the sameoperation_id, never a new one, or the action may run twice. A reused id can return the earlier result, so to repeat an action on purpose, use a new id. devapp.app.*Actions have no duplicate protection — every call runs. Pass the error'sdetails.operation_idtooperation.inspectfirst, and send again only if it shows the call was not dispatched (backenddocs/devapp-mcp.md).
- Built-in
room.actions.searchwith a multi-word query can return nothing. Useroom.actions.describe <exact name>, or search with no query and scan the list.- To hand off with
room.message.send, resolve the name first (room.member.resolve, never guess), then pass the mxid inmentionsand write it in the body too (the relay scans both). Parameters vary per room, soroom.actions.describe room.message.sendbefore relying onmentions.
What ships with it
26 files 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.
- _gateway.py 13 KB runs code
- authz.py 9.7 KB runs code
- display.py 6.6 KB runs code
- events_acceptance.py 10 KB runs code
- events.py 19 KB runs code
- gateway_credentials.py 30 KB runs code
- grant.py 5.1 KB runs code
- history_collection.py 3.4 KB runs code
- history-workflow.md 2.1 KB
- history.py 1.7 KB runs code
- join.py 1.9 KB runs code
- manifest.json 375 B
- media.py 6.3 KB runs code
- members.py 3.7 KB runs code
- mention.py 11 KB runs code
- react.py 2.7 KB runs code
- read.py 12 KB runs code
- receipt.py 2.2 KB runs code
- relations.py 1.7 KB runs code
- resolve.py 18 KB runs code
- room_ops.py 20 KB runs code
- room-ops-gate.json.example 386 B
- rooms.py 2.2 KB runs code
- say.py 8.8 KB runs code
- test_room_ops.py 78 KB runs code
- verify_platform_card.py 9.1 KB runs code
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.
- yesterday Changed · -4 lines 041e92bf8b77
- 2d ago Changed · -1 lines 778a263e8a59
- 10d ago Changed · +3 lines 09ea4e7a4c3a
- 11d ago Changed · +1 lines 020bf22e536c
- 15d ago Changed · +6 lines a4e712995e71
- 23d ago Changed · +46 lines 8df1c619b8e1
- 24d ago Changed · +6 lines e0520c5a9ec8
- 1mo ago Changed · +3 lines 6c91da8d10b8
- 1mo ago Changed · +5 lines 2beca4e0e571
- 1mo ago First seen · 282 lines · 0 tokens per session scan A 3d6bc09bc5a0
agent-room-ops is a skill published in the GitHub repository sonichi/sutando (399 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,486 tokens. 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 skills, from other repositories
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
app-builder
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…
assistant-migration
Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum…
guardian-verify-setup
Set up channel verification for phone, Telegram, Slack, Discord, or email channels via outbound verification flow.
stripe-link-wallet
Agent wallet on the Stripe Link CLI (link-cli). Connect the wallet, then buy, purchase and pay for things on the user's behalf via approved spend requests, one-time-use cards, and 402 / Machine Payment Protocol (MPP) payments.
vellum-memory-v2-migration
Perform a one-time migration from memory v1, to memory v2, which was introduced in 0.8.0.