agent-cold-start-diagnostic

To check operational completeness, score the agent's configuration artifacts against a rubric covering Identity, Decision Frameworks, Escalation, Task Specification, Rhythms, Memory, Error Handling, and Style. This diagnostic identifies missing components and suggests fixes to prevent silent failures.

Silent failures in agent configurations are caused by gaps in operational completeness, specifically missing decision frameworks, escalation rules, rhythms, and error handling. Running a diagnostic rubric against CLAUDE.md, agent.yaml, and memory files alerts you to these missing components.

Assess CLAUDE.md and agent.yaml files by applying a cross-reference validation against an eight-dimension operational completeness rubric. This process alerts you to missing escalation rules and provides a structured report with recommended fixes.

Yes, the operational completeness diagnostic applies to both single and multi-agent setups. It evaluates configuration artifacts including cron rhythms and memory files across the entire setup to identify gaps and suggest fixes.

Run an agent configuration health check before deploying a new agent persona, immediately after editing agent artifacts, or as a recurring governance check. This ensures ongoing operational readiness and catches gaps that cause silent failures.

The best way to score an agent's operational readiness is to evaluate its configuration artifacts against an eight-dimension rubric with cross-reference validation. This generates a structured report highlighting missing components, gaps, and recommended fixes.