setup-swarm

setup-swarm is a skill for Claude Code from Kasempiternal/Claude-Agent-System. It costs 25 tokens per session (662 once invoked), scanned B, original, MIT.

A setup guide that enables Claude Code’s experimental Agent Teams feature in its settings file. It supports the team and shared-task functions required by the Hydra and Legion swarm workflows.

In plain words
What is it for?
Enabling Agent Teams, confirming the user is ready, and updating Claude Code’s settings so multiple agents can work together.
Why use it?
It removes the manual configuration needed before those swarm workflows can run. It also warns users to close other Claude Code sessions first because changing settings while they are open can cause problems.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

Part of the cas plugin — 19 skills, 3 hooks, 2 MCP servers shipped together

Good fit Enabling Agent Teams, confirming the user is ready, and updating Claude Code’s settings so multiple agents can work together.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kasempiternal/claude-agent-system/setup-swarm
Install

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.

Any agent
npx skills add Kasempiternal/Claude-Agent-System --skill setup-swarm
Clone the repo
git clone --depth 1 https://github.com/Kasempiternal/Claude-Agent-System

Made for: Claude Code.

Or install cas, the plugin that ships this one along with the rest of its 19 skills, 3 hooks, 2 MCP servers.

Wrote 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.

agentmods badge for setup-swarm

README.md
[![agentmods](https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/setup-swarm.svg)](https://agentmods.dev/skills/kasempiternal/claude-agent-system/setup-swarm)
Your own site
<a href="https://agentmods.dev/skills/kasempiternal/claude-agent-system/setup-swarm"><img src="https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/setup-swarm.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 662 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00662
Opus 5 $0.00013 $0.00331
Sonnet 5 $0.00005 $0.00132
Haiku 4.5 $0.00003 $0.00066

Measured 8d ago against content hash d61c1da3804c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

setup-swarm 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 8d 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.

You are the CAS Swarm Setup assistant. Your job is to enable the Agent Teams experimental feature in the user's `~/.claude/settings.json`.
claude-agent-system-plugin/skills/setup-swarm/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the CAS Swarm Setup assistant. Your job is to enable the Agent Teams experimental feature in the user's ~/.claude/settings.json.

⚠️ SESSION WARNING — SHOW THIS FIRST

Before doing anything else, display this warning:

⚠️  IMPORTANT: This skill edits ~/.claude/settings.json (Claude Code's brain).
    Editing settings while other Claude Code sessions are running can crash
    or corrupt those sessions.

    → Close ALL other Claude Code sessions before continuing.

Then use AskUserQuestion to confirm:

  • "I've closed all other sessions — proceed" (recommended)
  • "Cancel"

If the user cancels, stop immediately.

What This Enables

The CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS environment variable, which unlocks:

  • TeamCreate / TeamDelete — create and manage agent teams
  • TaskCreate / TaskUpdate / TaskList — shared task lists across teammates
  • SendMessage — inter-agent communication
  • Agent spawning with team_name — teammates that join a shared team

These are required by /hydra (multi-task parallel swarm) and /legion (iterative swarm loop).

Installation Steps

Step 1: Read existing settings

Read ~/.claude/settings.json. If it doesn't exist, start with {}.

Step 2: Check if already enabled

Look for env.CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS set to "1".

If already enabled, tell the user:

✓ Agent Teams is already enabled in your settings.
  You're ready to use /hydra and /legion.

And stop — no changes needed.

Step 3: Merge the env config

Add the env variable to settings. Do not remove any existing env variables or other config — merge alongside them.

The config to add:

{
  "env": {
    "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
  }
}

If env already exists with other variables, add CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS to the existing object.

Step 4: Write settings and confirm

Write the merged ~/.claude/settings.json with proper formatting (2-space indent).

Read the full file on GitHub · 94 lines

Changes

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.

  1. 8d ago First seen · 94 lines · 25 tokens per session scan B d61c1da3804c

Subscribe to this mod's changes

setup-swarm is a skill published in the GitHub repository Kasempiternal/Claude-Agent-System (15 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 662 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

review

Review code with parallel agents — tests, security, Ecto, LiveView, Oban. Use after implementation to catch bugs and anti-patterns before committing.

oliver-kriska/claude-elixir-phoenix · 34 tokens

audit

Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.

oliver-kriska/claude-elixir-phoenix · 35 tokens

pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 59 tokens

phx-pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 61 tokens

boundaries

Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.

oliver-kriska/claude-elixir-phoenix · 33 tokens

challenge

Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.

oliver-kriska/claude-elixir-phoenix · 34 tokens