gadaalabs/claude-code-on-steroids/legion

Claude Code and agent skill by gadaalabs/claude-code-on-steroids

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Select optimal subagent topology (hierarchical, mesh, ring, star) based on task structure; adds Ruflo-style swarm intelligence to Superpowers

Install

npx vskill@latest install gadaalabs/claude-code-on-steroids/legion

SKILL.md

Swarm Coordination

Overview

LEGION — A legion is a large, coordinated force organized into precise, independent units. When invoked: selects the optimal agent topology for the task — parallel (independent tasks), pipeline (sequential stages), hierarchical (orchestrator + specialists), or mesh (peer review) — and coordinates execution across all agents.

Core principle: Match agent topology to task structure — the right coordination pattern prevents chaos and maximizes parallelism.

Announce at start: "Running LEGION to select agent topology and coordinate."

Topology Selection

Independent tasks, no coordination needed → STAR (see patterns/star.md) Sequential stages, each transforms previous output → RING (see patterns/ring.md) Exploration, multiple hypotheses, no clear structure → MESH (see patterns/mesh.md) Plan execution, coordinator + specialists → HIERARCHICAL (see patterns/hierarchical.md)

Load the matching pattern file for full prompt templates and examples.

Quick Reference

TopologyParallelismBest For
HierarchicalModeratePlan execution, structured tasks
MeshHighExploration, research, bug investigation
RingLow (sequential)Data pipelines, multi-stage transforms
StarVery HighIndependent parallel work, batch processing

Swarm Size Guidelines

Task ComplexitySwarm SizeTopology
Single file edit1 agentN/A (no swarm)
2-5 files2-3 agentsHierarchical
5-10 files3-5 agentsHierarchical or Star
Multi-module5-7 agentsHierarchical-Mesh
System-wide7-15 agentsAdaptive with phases
10 agents: coordination overhead exceeds parallelism benefit. >15 agents: decompose into separate projects.

Hybrid: Hierarchical-Mesh (Adaptive)

Complex projects with both exploration and execution:

PHASE 1: Exploration (Mesh) — explore angles, synthesize requirements
PHASE 2: Planning (Hierarchical) — coordinator writes plan, decomposes tasks
PHASE 3: Execution (Hierarchical) — workers execute, coordinator reviews
PHASE 4: Integration (Mesh) — collective debugging and integration

Consensus for Disagreement Resolution

Majority: 3 agents agree A, 2 agree B → proceed with A, document dissent. Weighted: Security decision → security-architect vote 3x weight. Byzantine: f < n/3 faulty agents. With 4 agents: tolerate 1 faulty opinion. If no majority → escalate to human.

Swarm Auto-Triggering

Auto-trigger when ALL of:

  1. Task touches 3+ independent files
  2. No sequential dependency between changes
  3. Total estimated work > 20 minutes single-threaded

Auto-trigger announcement:

DETECTING: This task touches N independent files with no cross-dependencies.
AUTO-TRIGGERING: <topology> swarm (N spokes/workers)
Topology rationale: [reason]

Do NOT auto-trigger for: bug fixes (investigate first), tasks < 3 files, shared state changes.

Integration with Existing Skills

SkillIntegration
phantomHierarchical topology by default
architectMesh topology for exploration phase
hunterMesh topology for multi-angle investigation
blueprintPlan should specify recommended topology
tribunalStar topology for parallel file review

Red Flags

Never:

  • Use Ring when tasks are independent (waste of parallelism)
  • Use Mesh for implementation (no coordination = chaos)
  • Use Hierarchical for exploration (coordinator bottlenecks creativity)
  • Use Star when subtasks have dependencies (integration fails)
  • Deploy >10 agents without clear coordination plan

Final Rule

Topology determines success — match structure to task
Hierarchical for execution | Mesh for exploration
Ring for pipelines | Star for parallel work

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
67
Repository forks
10
7-day trend score
21

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/gadaalabs/claude-code-on-steroids/legion/badge)](https://verified-skill.com/skills/gadaalabs/claude-code-on-steroids/legion)

Something wrong with this skill or its page? Tell us.