Multi-agent harness for long-running AI application development. Planner-Generator-Evaluator architecture with progressive simplification. Claude Code plugin.
-
Updated
Mar 29, 2026 - Shell
Multi-agent harness for long-running AI application development. Planner-Generator-Evaluator architecture with progressive simplification. Claude Code plugin.
Architectural pattern for the multi-agent coordination layer above PDS and MCP. Adversarial verification, file-system state, negotiated contracts, Planner/Generator/Evaluator role decomposition. Companion spec to Progressive Discovery Spine.
Add a description, image, and links to the planner-evaluator topic page so that developers can more easily learn about it.
To associate your repository with the planner-evaluator topic, visit your repo's landing page and select "manage topics."