Hardening Agent Intake via Empirical Verification & Historical Domain Querying

Architectural Paradox

Currently, the ticket-intake skill relies on "agent intuition" (e.g., asking "didn't we try this before?") to trigger historical verification against the Memory Core. However, fresh Swarm instances suffer from "Zero-State Amnesia" and inherently lack intuition. Additionally, agents tend to blindly accept prescribed architectural solutions within tickets instead of isolating the true root cause, leading to Negative ROI.

Resolution

This ticket formalizes two systemic mandates across the Neo.mjs Agent OS:

1. Historical Amnesia Check (Unknown Unknowns): Agents MUST explicitly perform a blind domain query (query_documents, query_summaries, query_raw_memories) against the Memory Core regardless of how novel a ticket seems.
2. Empirical Proof (Test-Driven Discovery): Agents MUST explicitly validate technical hypotheses by writing localized Playwright tests via the unit-test skill before mutating live architecture.

Definition of Done

• Update .agent/skills/ticket-intake/references/ticket-intake-workflow.md with the new Historical Amnesia (Unknown Unknowns) and Empirical Proof mandates.
• Update .agent/skills/pull-request/references/pull-request-workflow.md to require missing unit tests as a pre-commit block for "Minor Gaps".