Deploy fleets of specialized AI agents that scout, plan, implement, and review your code—all running in parallel.
Each skill orchestrates a different swarm topology—from intelligent routing to iterative autonomous loops and adversarial verification.
Analyzes your task and automatically picks the best skill—Siege, Legion, Hydra, PCC-Opus, or PCC—so you don't have to.
auto-routingSonnet scouts explore the codebase in parallel, then Opus implementers execute the plan with precision.
scout + implementMaximum exploration quality. Opus-powered scouts for when the codebase is complex and nuance matters.
max qualitySpawns fresh claude -p sessions per iteration with two-skeptic adversarial verification. Arithmetic-only exit decisions.
Submit a holistic project. Legion keeps deploying swarms autonomously until everything is built or progress stalls.
beta — autonomous loopSubmit N tasks at once. Agents collaborate via mailbox messaging within waves. Two-skeptic adversarial global verification.
beta — n-task parallelSeven specialized review agents analyze bugs, style, silent failures, comments, types, and test coverage simultaneously.
7 agentsLyra AI optimization with triple review gates. The full pipeline—routing, implementation, and validation.
full pipelineYou give the task. CAS splits it into parallel workstreams, assigns specialized agents, and synthesizes their output.
Run a skill like /pcc with your task description.
Parallel scout agents map the codebase, finding patterns and relevant files.
Implementer agents work concurrently, each owning their file set exclusively.
Results are deduplicated, cross-referenced, and presented as one cohesive deliverable.
The multi-headed orchestrator uses Claude Teams—a shared task list, message passing, and wave-based execution to run N tasks with zero file conflicts.
Install in one command. No configuration needed.