agent-dispatch
Agent Dispatch analyzes feature dependencies and creates topologically sorted batches of parallel agent work, ensuring interdependent features never execute concurrently. Use this when coordinating multiple agents on features with complex prerequisite relationships to maximize throughput while maintaining execution order constraints.
git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/agent-dispatch && cp -r /tmp/agent-dispatch/library/methodologies/automaker/skills/agent-dispatch ~/.claude/skills/agent-dispatchSKILL.md
# Agent Dispatch Build dependency-aware, batched dispatch queues for parallel agent execution. ## Agent Feature Planner - `automaker-feature-planner` ## Workflow 1. Analyze inter-feature dependencies 2. Build directed acyclic graph (DAG) 3. Generate topologically sorted execution order 4. Group features into batches respecting concurrency limits 5. Ensure no batch contains interdependent features 6. Assign agent types to each feature ## Inputs - `projectName` - Project name - `orderedPlans` - Feature plans in dependency order - `maxParallel` - Maximum concurrent agents - `dependencyGraph` - Feature dependency graph ## Outputs - Batched dispatch queue with agent assignments ## Process Files - `automaker-feature-pipeline.js` - Stage 5 - `automaker-orchestrator.js` - Phase 3 (batching)
Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
Architect code review with DRY, YAGNI, abstraction, and test coverage principle enforcement