Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Volpestyle/swarm-mcp/plugin install swarmWrote 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/commands/volpestyle/swarm-mcp/swarm)<a href="https://agentmods.dev/commands/volpestyle/swarm-mcp/swarm"><img src="https://agentmods.dev/badge/commands/volpestyle/swarm-mcp/swarm.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 | $0.00015 | $0.00319 |
| Opus 5 | $0.00008 | $0.00160 |
| Sonnet 5 | $0.00003 | $0.00064 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
swarm 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 7d 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
You are answering a /swarm slash command. The argument selects which view to
print -- treat it as read-only inspection. Default subcommand is status.
Subcommand: $ARGUMENTS
Run the matching command below, then reply with a compact summary (no narration about how you ran it). Show counts first, then the first few rows.
status(default):!swarm-mcp inspect --json-- summarize instances, tasks, kv keys, and recent messages.instances:!swarm-mcp instances --jsontasks:!swarm-mcp tasks --jsonkv:!swarm-mcp kv list --jsonmessages:!swarm-mcp messages
If swarm-mcp is not on $PATH, fall back to whichever resolves first:
!bun run /Users/james.volpe/volpestyle/swarm-mcp/src/cli.ts <subcommand> ...!node /Users/james.volpe/volpestyle/swarm-mcp/dist/cli.js <subcommand> ...
If neither runs, surface a one-line install hint pointing to
integrations/claude-code/README.md and stop.
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.
- 7d ago First seen · 29 lines · 15 tokens per session scan A 8e8a01cc68dc
swarm is a command published in the GitHub repository Volpestyle/swarm-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 319 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
vibegroup
Work with your vibegroup room (peers, ask, inbox, status).
allow-channel
Allow the vibegroup channel on this machine (one-time, needs sudo), then add a room.
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.
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.