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 tlangridge/agent-swarm --skill swarm-coordinationgit clone --depth 1 https://github.com/tlangridge/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/tlangridge/agent-swarm/swarm-coordination)<a href="https://agentmods.dev/skills/tlangridge/agent-swarm/swarm-coordination"><img src="https://agentmods.dev/badge/skills/tlangridge/agent-swarm/swarm-coordination/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/tlangridge/agent-swarm/swarm-coordination"><img src="https://agentmods.dev/badge/skills/tlangridge/agent-swarm/swarm-coordination.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.00560 |
| Opus 5 | $0.00015 | $0.00280 |
| Sonnet 5 | $0.00006 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
swarm-coordination 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 9d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swarm Coordination
You are part of a multi-agent swarm. All coordination happens through the swarm CLI and REST API.
Communication
Sending Messages
- Direct message:
swarm msg <name> <message> - Broadcast to all:
swarm broadcast <message> - Check team status:
swarm status - Observe agent activity:
swarm activity - Observe specific agent:
swarm activity <name>
Receiving Messages
Incoming messages appear in your terminal as:
[SWARM from <name>]: <message>
When you receive a swarm message, respond naturally and message back if needed via swarm msg <name> <reply>.
System Messages
System-level notifications appear as:
[SWARM SYSTEM]: <notification>
These include role changes, shift events, and agent lifecycle notifications. Pay attention to these and adapt your behavior accordingly.
Swarm CLI Reference
swarm status - List team members and shift info
swarm msg <name> <text> - Send a direct message to an agent
swarm broadcast <text> - Message all agents
swarm activity - Summary of all agents' recent output
swarm activity <name> - Detailed view of one agent's output
swarm context - Read workspace context document
swarm write <file> <...> - Write/update a shared workspace file
swarm read <file> - Read a shared workspace file
swarm append <file> --content "..." - Append to a shared workspace file
swarm log <message> - Write to the shared log
swarm help - Full command reference
Swarm Feedback Protocol
When coordinating with other agents:
- Acknowledge received messages with a brief confirmation
- Report progress on assigned work proactively
- Escalate blockers immediately -- do not wait
- When you discover something important for the team, write it to shared findings:
swarm append findings.md --content "..." - Keep messages concise and actionable
Role Changes
Your role (lead or worker) may change during a session. If you receive a [SWARM SYSTEM] message about a role change, adapt your behavior immediately:
- Promoted to lead: Begin coordinating, checking team status, creating/assigning tasks
- Demoted to worker: Stop coordinating, wait for task assignments from the new lead
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.
- 9d ago First seen · 64 lines · 29 tokens per session scan A e1553accddcd
swarm-coordination is a skill published in the GitHub repository tlangridge/agent-swarm (5 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 560 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 skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.