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 commands/wybe-labs/session-multiplayer/sm-sendgit clone --depth 1 https://github.com/wybe-labs/session-multiplayerWhat 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 | $0.00011 | $0.00268 |
| Opus 5 | $0.00005 | $0.00134 |
| Sonnet 5 | $0.00002 | $0.00054 |
| Haiku 4.5 | $0.00001 | $0.00027 |
Grade A, and why
sm-send scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Send a message with the session-multiplayer MCP server's send_message tool with priority "normal" (it will reach the recipients' agent sessions when their current turn finishes — use /sm-interrupt for urgent barge-ins, or priority "passive" if I say it's non-urgent inbox mail). The first word of "$ARGUMENTS" is the room name and the rest is the message — but if the first word doesn't match any room in status, and I'm only in one room, send the whole text there instead.
If the message is meant for specific people — it starts with "to :" or "@name", or I phrase it like "tell bob …" — put those display names (as they appear in status) in the tool's to list and strip the addressing prefix from the message text. Everyone in the room still gets the message in their chat log/inbox, but only the named people get active delivery; the others aren't interrupted. Without to, the whole room gets it at the send priority.
Confirm whether it was delivered live or queued for later, and to whom it was addressed if I named recipients.
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.
- 2d ago First seen · 11 lines · 11 tokens per session scan A 5e794c970ff5
sm-send is a command published in the GitHub repository wybe-labs/session-multiplayer (3 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 268 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.