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.
$npx -y skills add onewave-ai/claude-skills --skill agent-armyInstalls into the current project.
Run `npx skills use "https://github.com/onewave-ai/claude-skills" --skill "onewave-ai/claude-skills/agent-army"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/onewave-ai/claude-skills" that are relevant to the current task. Run `npx skills add "https://github.com/onewave-ai/claude-skills"` and select the relevant skills, then follow their instructions.