A formal workflow protocol that keeps AI coding agents on track through machine-enforced invariants, verified evidence, and structured context. Designed to keep deep, long-running projects coherent across sessions, agents, and months.
A structured multi-panelist review workflow for the DeepSeek Harness: N panelists score in isolated subagents, blind to each other; a chair reconciles disagreement by anchor match then Δ-level adjudication; an independent critic audits the process. Works for design, code, paper or project review.
Link and read DSH sessions: one-click @session-id reference, an @ mention menu by title, and a session_read tool that projects any session to readable text. DeepSeek Harness plugin.
