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 skills/sonichi/sutando/agent-room-opsnpx 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.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 5.1 | $0.00000 | $0.03494 |
| Opus 5 | $0.00000 | $0.01747 |
| Sonnet 5 | $0.00000 | $0.00699 |
| Haiku 4.5 | $0.00000 | $0.00349 |
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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 232 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
One skill, multiple tools. Everything an agent does in a room beyond its task
inbox lives here as a tool, so the parity capabilities are self-evidently one
collection (not N scattered skills). Each tool is a thin gateway-only client
verb sharing _gateway.py; the gateway/broker (box-side) owns the platform creds and
does the privileged Matrix ops + authoritative membership enforcement.
Collection name
agent-room-ops(provider-agnostic; alts:room-participant,agent-chat-io). Platform-tied names (e.g.matrix-agent) are avoided.
Tools
| tool | purpose | parity vs a chat bot-client |
|---|---|---|
read <room> |
pull recent room history | discord att.save-context / channel read |
fetch <ref> |
inbound media → local path | discord inbound att.save→inbox |
send <room> <path> |
outbound file/image upload | discord outbound [file:] |
say <room> <text> |
post plain text, mentioning no one — status lines, an answer to the room | discord plain channel message |
react <room> <event> |
add an m.reaction (ack) |
discord add_reaction (👀/✅) |
unreact <room> <event> |
remove the agent's reaction | discord remove-on-reply |
join <room> |
accept the agent's own pending invite | discord guild-join on invite |
doc get|put|rm <room> |
read/write/delete the room's shared Room Context docs (context, todo, memos — or any agent-defined folder) | the durable-state half: like a pinned channel wiki the bot can edit |
python3 skills/agent-room-ops/room_ops.py read '!room:hs' --limit 20 --agent '@a:hs'
python3 skills/agent-room-ops/room_ops.py fetch 'mxc://hs/abc' --room '!room:hs' --agent '@a:hs'
python3 skills/agent-room-ops/room_ops.py send '!room:hs' /tmp/pic.png --caption 'fig 1' --agent '@a:hs'
python3 skills/agent-room-ops/room_ops.py react '!room:hs' '$evt' --ack received --agent '@a:hs'
python3 skills/agent-room-ops/room_ops.py unreact '!room:hs' '$evt' --ack received --agent '@a:hs'
python3 skills/agent-room-ops/room_ops.py say '!room:hs' 'deploy finished, 3 green' --agent '@a:hs'
# -> {"ok":true,"state":"confirmed|unconfirmed","event_id":...}. `confirmed` means an
# event id came back. `unconfirmed` is a 200 with no proof: the send probably landed, so do
# NOT re-send blindly, but do not drop a fallback/result path on it either.
# Use `mention` instead when a specific agent must be triggered; `say` never pings.
python3 skills/agent-room-ops/room_ops.py say '!room:hs' 'on it' --reply-to '$evt' --agent '@a:hs'
# --reply-to (on `say` and `mention`) CITES the message being replied to. The post stays
# in the MAIN TIMELINE — it is not thread membership. Only a relation with
# rel_type m.thread puts an event in a thread, and the gateway has no field for that,
# so room-ops deliberately offers no way to ask for one: a call that reported success
# while landing outside the requested thread is the failure worth refusing. A malformed
# event id is REFUSED before the network rather than posted uncited.
python3 skills/agent-room-ops/room_ops.py join '!room:hs' --agent '@a:hs'
python3 skills/agent-room-ops/room_ops.py doc get '!room:hs' --folder room-todo --name TODO.md --agent '@a:hs'
python3 skills/agent-room-ops/room_ops.py doc put '!room:hs' --folder room-memo --name note.md --file /tmp/note.md --agent '@a:hs'
python3 skills/agent-room-ops/room_ops.py doc rm '!room:hs' --folder room-memo --name note.md --agent '@a:hs'
python3 skills/agent-room-ops/room_ops.py grant '!room:hs' --tier '@u:hs=owner' --default-tier guest --agent '@a:hs'
python3 skills/agent-room-ops/room_ops.py events emit '!room:hs' --type space.ag2.app.card --content '{"k":1}' --agent '@a:hs'
# -> one typed space.ag2.* TIMELINE event sent AS this agent. Same
# confirmed/unconfirmed receipt as `say`. Which type namespaces are accepted is the
# server's rule, not restated here — a refusal arrives as `reason`.
# Timeline needs no power-level grant; `op:state` (roomtype/widget) does.
What ships with it
25 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 12 KB runs code
- authz.py 9.5 KB runs code
- display.py 6.4 KB runs code
- doc_sync.py 14 KB runs code
- doc.py 6.0 KB runs code
- events_acceptance.py 10 KB runs code
- events.py 19 KB runs code
- gateway_credentials.py 5.3 KB runs code
- grant.py 4.9 KB runs code
- join.py 1.8 KB runs code
- manifest.json 318 B
- media.py 6.1 KB runs code
- members.py 3.1 KB runs code
- mention.py 6.3 KB runs code
- react.py 2.7 KB runs code
- read.py 11 KB runs code
- receipt.py 2.0 KB runs code
- relations.py 1.4 KB runs code
- resolve.py 4.9 KB runs code
- room_ops.py 15 KB runs code
- room-ops-gate.json.example 386 B
- rooms.py 2.0 KB runs code
- say.py 5.7 KB runs code
- test_room_ops.py 70 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.
- 6d ago First seen · 232 lines · 0 tokens per session scan A 21e974d6e695
agent-room-ops is a skill published in the GitHub repository sonichi/sutando (391 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,494 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
contacts
Manage contacts, communication channels, access control, and invite links.
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
guardian-verify-setup
Set up channel verification for phone, Telegram, Slack, Discord, or email channels via outbound verification flow.
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…
vellum-memory-v2-migration
Perform a one-time migration from memory v1, to memory v2, which was introduced in 0.8.0.