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 mpesavento/swarmbus --skill using-swarmbusgit clone --depth 1 https://github.com/mpesavento/swarmbusWrote 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/mpesavento/swarmbus/using-swarmbus)<a href="https://agentmods.dev/skills/mpesavento/swarmbus/using-swarmbus"><img src="https://agentmods.dev/badge/skills/mpesavento/swarmbus/using-swarmbus.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 | $0.00124 | $0.03587 |
| Opus 5 | $0.00062 | $0.01793 |
| Sonnet 5 | $0.00025 | $0.00717 |
| Haiku 4.5 | $0.00012 | $0.00359 |
Grade B, and why
using-swarmbus scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**MCP mode** — you have the tools `send_message`, `read_inbox`, `watch_inbox`, `list_agents` available as direct function calls. Used by Claude Code when the swarmbus MCP sidecar is registered in `~/.claude/settings.json How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using swarmbus — Peer Agent Messaging
swarmbus is a pub/sub layer that lets parallel agent sessions exchange messages through an MQTT broker. Each agent is a peer; there is no central server and no orchestrator. You have been registered with an agent-id; every operation below is available in two forms — use whichever matches your host.
Detect your mode first
Before calling anything, pick the form that matches your environment:
MCP mode — you have the tools send_message, read_inbox, watch_inbox, list_agents available as direct function calls. Used by Claude Code when the swarmbus MCP sidecar is registered in ~/.claude/settings.json.
CLI mode — you do not have those MCP tools, but you have a shell. Run the swarmbus command. Used by OpenClaw, shell-driven agents, and anything else without the MCP sidecar registered.
If you're not sure, try swarmbus --help first. If that works, use CLI mode. If MCP tools are in your tool list, prefer MCP mode (less latency, no shell round-trip).
digraph mode_selection {
"Need to send/read a message" [shape=doublecircle];
"`send_message` in tool list?" [shape=diamond];
"Use MCP tools" [shape=box];
"`swarmbus --help` resolves?" [shape=diamond];
"Use `swarmbus` CLI" [shape=box];
"Not installed — stop and ask user" [shape=box];
"Need to send/read a message" -> "`send_message` in tool list?";
"`send_message` in tool list?" -> "Use MCP tools" [label="yes"];
"`send_message` in tool list?" -> "`swarmbus --help` resolves?" [label="no"];
"`swarmbus --help` resolves?" -> "Use `swarmbus` CLI" [label="yes"];
"`swarmbus --help` resolves?" -> "Not installed — stop and ask user" [label="no"];
}
Operations
| Intent | MCP form | CLI form |
|---|---|---|
| Send to a peer | send_message(to, subject, body, content_type?) |
swarmbus send --agent-id <me> --to <peer> --subject "..." --body "..." |
| Read from daemon's inbox file (use when daemon is running) | (use file directly) | swarmbus tail --agent-id <me> (add --follow to stream) |
| Drain MQTT queue, exit (no-daemon contexts) | read_inbox() |
swarmbus read --agent-id <me> (add --json for structured output) |
| Block until a message arrives (no-daemon contexts) | watch_inbox(timeout=30) |
swarmbus watch --agent-id <me> --timeout 30 |
| Who's online? | list_agents() |
swarmbus list |
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 · 242 lines · 124 tokens per session scan B 5876ec2aaf83
using-swarmbus is a skill published in the GitHub repository mpesavento/swarmbus (11 stars, last pushed 3mo ago), licensed MIT. It adds 124 tokens to every session and 3,587 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…