agentrigs
+ submit rig
~ / rigs / ben-alkov / the_swarm

ben-alkov/the_swarm

Claude Code plugin for multi-pattern multi-agent orchestration, using CC's built in Agent Swarm as the engine — dispatches and coordinates specialist sub-agents in fan-out, pipeline, map-reduce, speculative, and swarm configurations.

↗ GitHub ★ 5 NOASSERTION updated 4mo ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~671 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/ben-alkov/the_swarm

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit ben-alkov/the_swarm/src/skills/swarm-fan-out .claude/skills/swarm-fan-out
$ npx degit ben-alkov/the_swarm/src/skills/swarm-map-reduce .claude/skills/swarm-map-reduce
$ npx degit ben-alkov/the_swarm/src/skills/swarm-pipeline .claude/skills/swarm-pipeline
$ npx degit ben-alkov/the_swarm/src/skills/swarm-speculative .claude/skills/swarm-speculative
$ npx degit ben-alkov/the_swarm/src/skills/swarm-swarm .claude/skills/swarm-swarm
$ npx degit ben-alkov/the_swarm/src/skills/swarm .claude/skills/swarm

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(~/.aws/**)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/.env.*)",
      "Read(**/*.key)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(npm publish:*)",
      "Bash(wget *)",
      "Bash(git rebase *)",
      "Bash(gh pr merge *)",
      "Bash(git commit *)"
    ]
  }
}

Skills (6)

swarm-fan-outswarm-map-reduceswarm-pipelineswarm-speculativeswarm-swarmswarm

Similar rigs

ethersphere/swarm-quickstart-skills
Hands-on onboarding guides for developers building on Swarm — step-by-step skills for Claude Code covering node setup, uploads, website hosting, feeds, dApps, and more
★ 9 project Claude Code 13 skills 3mo ago
Skill Collector 2.6k tok ·
guaardvark/guaardvark
The self-hosted AI studio: local video, image, music, voice, LoRA training, coding swarms, RAG and screen agents on one GPU, driven from the Studio or by your coding agent (Claude Code, Cursor, Codex, OpenClaw) through MCP and skills.
★ 244 project Codex 15 skills 7d ago
Skill Collector 912 tok ·
iamvonpasion/hashb
Dev workflow toolkit for Claude Code — 14 skills that turn AI into a structured development partner. Spec → Design → Eng → TDD → Review → QA → Ship.
★ 2 project Claude Code 20 skills 1 agents 5mo ago
Skill Collector 2.5k tok ·
langchain-ai/langchain-skills
—
★ 1,265 collection Codex 22 skills 14d ago
Skill Collector 2.1k tok ·
copied ✓