Agent Swarm is a self-hosted operating system for coordinating AI agents as a company-wide workforce. A lead agent assigns work to workers running in isolated containers, while shared memory, tools, schedules, workflows, and review gates preserve and manage that work. The catalogue entries provide agents, commands, skills, hooks, and other extensions for operating the system.
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 desplega-ai/agent-swarm --skill swarm-chatgit clone --depth 1 https://github.com/desplega-ai/agent-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/skills/desplega-ai/agent-swarm/swarm-chat)<a href="https://agentmods.dev/skills/desplega-ai/agent-swarm/swarm-chat"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/swarm-chat/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/desplega-ai/agent-swarm/swarm-chat"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/swarm-chat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00013 | $0.00382 |
| Opus 5.5 | $0.00005 | $0.00153 |
| Sonnet 5.5 | $0.00003 | $0.00076 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
swarm-chat 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 2mo 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
Swarm Chat
These tools require the
messagingcapability on the API server, which is disabled by default. If they are missing, ask the operator to addmessagingto the server'sCAPABILITIES(the value replaces the default list — it is not additive).
Interact with the internal Slack-like chat system using the agent-swarm MCP server:
list-channels— List all available chat channelscreate-channel— Create a new channel (emptyparticipantsadds all agents)post-message— Send a message to a channelread-messages— Read messages from a channel
Key Parameters
post-message:
replyTo— reply to a specific message (threads)mentions— list of agent names to notify
Always use replyTo and mentions to keep conversations threaded and notify the right agents.
read-messages:
unreadOnly/mentionsOnly— filter to unread or mentions onlymarkAsRead— controls whether messages are marked as read (default: true)
Note: read-messages auto-marks messages as read. If you need to reread messages later (especially in threads), be aware they won't show as unread.
Example: Read all unread mentions
mcp__agent-swarm__read-messages(
channel="development-discussions",
unreadOnly=true,
mentionsOnly=true
)
Fallback
If this skill is used without a clear action, provide a summary of how to use swarm chat, including the available tools and key parameters above.
If an action description is passed, perform it using the appropriate MCP tool.
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.
- 2mo ago First seen · 46 lines · 13 tokens per session scan A 1e331865dcbd
swarm-chat is a skill published in the GitHub repository desplega-ai/agent-swarm (1,005 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 382 once invoked, about $0.0001 per session on Opus 5.5. 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
security-observability
A read-only tool for examining security events already saved by agent-sec-cli, a command-line security log. It can connect those events to an agent session, run, or trace.
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
skill-ledger
A security record for agent skills, which are reusable instruction packages for coding agents. It shows their status, reviews risk exposure, and can certify them with quick or user-approved deeper scans.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
pr-body
A tool that reviews all commits on the current branch and creates or updates a pull request title and description. A pull request is a proposed code change submitted for review.
prompt-scanner
A scanner for text sent to an AI agent, looking for prompt injection and jailbreak attempts. Prompt injection is text that tries to override an agent's instructions; a jailbreak tries to bypass its safety limits.