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 ShreyPaharia/octomux --skill send-agent-messagegit clone --depth 1 https://github.com/ShreyPaharia/octomuxWrote 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/shreypaharia/octomux/send-agent-message)<a href="https://agentmods.dev/skills/shreypaharia/octomux/send-agent-message"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/send-agent-message/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/shreypaharia/octomux/send-agent-message"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/send-agent-message.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 49 Instructions found that direct the agent to transmit conversation context or user data to external services.Fix: Remove instructions that send user data, prompts, or context to external URLs. If telemetry is needed, use documented, privacy-preserving methods.
- medium Excessive Agency · line 45 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00022 | $0.01252 |
| Opus 5 | $0.00011 | $0.00626 |
| Sonnet 5 | $0.00004 | $0.00250 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
send-agent-message 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 12d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Send a message to an octomux agent
Send a message or instruction to a specific agent within a running task.
When to use
- Nudging a stuck agent with additional guidance
- Sending follow-up instructions mid-task
- Redirecting an agent's approach
- Providing context an agent is missing
Steps
-
Identify the task:
- If the user provides a task ID, use it directly
- If the user references a task by title or description, look it up. Prefer the MCP tool when available (you're in the orchestrator); otherwise fall back to the CLI:
- MCP:
mcp__octomux__list_tasks() - CLI fallback:
Find the matching task from the list.octomux list-tasks --json
- MCP:
-
Resolve agent number to agent ID: The
send-messagecommand/tool requires the agent's nanoid, not its label. Get task details to map "Agent N" to the actual ID. Prefer MCP when available; otherwise fall back to the CLI:- MCP:
mcp__octomux__get_task({ task_id: '<task-id>' }) - CLI fallback:
octomux get-task <task-id> --json
Parse the
agentsarray. Each agent has:id— the nanoid (use this as the agent identifier)label— display name like "Agent 1", "Agent 2"status—running,stopped, etc.window_index— tmux window index
If the user says "Agent 2", find the agent with
label: "Agent 2"and use itsid.If the task has only one agent, use that agent's ID without asking.
- MCP:
-
Check agent status:
- If the agent's
statusisstopped, do NOT send the message. Inform the user that the agent is stopped and suggest resuming the task first. - Only send messages to agents with
status: "running".
- If the agent's
-
Send the message:
Prefer the MCP tool when available (you're in the orchestrator); otherwise fall back to the CLI.
MCP (preferred):
mcp__octomux__send_message({ task_id: '<task-id>', message: '<message>', })CLI fallback:
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.
- 12d ago First seen · 135 lines · 22 tokens per session scan A f9fc88c30848
send-agent-message is a skill published in the GitHub repository ShreyPaharia/octomux (22 stars, last pushed 10d ago), licensed MIT. It adds 22 tokens to every session and 1,252 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 2026-08-30.
Other skills, from other repositories
orcast
Use when orchestrating multiple agents in Orca: fan out parallel workers, pipeline work across stages, adversarially verify findings, run judge panels or loop-until-dry sweeps, or delegate a task and get the result back. You write a Plan definition in real JavaScript — a worker-workflow graph of worker, action, and…
muster
Coordinate with other coding-agent sessions — any machine, any vendor — on this repo via the muster CLI. Use when the user says /muster, asks to join or check a fleet, mentions muster, or wants to coordinate work with other sessions/machines on this repo.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
after-sales
Use when managing post-purchase experience, building customer loyalty, or increasing repeat purchases.
bankr
AI-powered crypto trading agent and LLM gateway via natural language. Use when the user wants to trade crypto, check portfolio balances, view token prices, transfer crypto, manage NFTs, use leverage, bet on Polymarket, deploy tokens, set up automated trading, sign and submit raw transactions, or access LLM models…
bankr-signals
Transaction-verified trading signals on Base blockchain. Agents publish trades.