OpenAgentSkill Registry Manifest
Skill: agent-army
Slug: onewave-ai-agent-army
Category: security
Description: Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

Agent fit:
- Decision: 70/100 Prototype first
- Primary fit: GitHub automation
- Role: Fallback candidate

Supply profile:
- Track: Coding and developer agents
- Scenario: GitHub automation
- Applicable agents: Claude Code, CLI, Codex, Cursor
- Maintenance: 28d since push
- Risk: Needs review

Trust:
- Trust score: 72/100 Strong shortlist
- Audit: 78/100 Needs review

Attribution:
- Status: Registry indexed
- Source: github fast track
- Creator: OneWave-AI
- Claim URL: https://www.openagentskill.com/skills/onewave-ai-agent-army#claim-this-skill

Install:
npx skills add OneWave-AI/claude-skills --skill agent-army

URLs:
- Web: https://www.openagentskill.com/skills/onewave-ai-agent-army
- API: https://www.openagentskill.com/api/agent/skills/onewave-ai-agent-army
- Install API: https://www.openagentskill.com/api/skills/onewave-ai-agent-army/install
- Repository: https://github.com/OneWave-AI/claude-skills/tree/main/agent-army