Run Agent Evaluation

Compare coding agents head-to-head on reproducible tasks with pass rate, cost, time, and consistency metrics.

Execute the full AgentHub competition lifecycle in a single command: initialize, capture baseline, spawn agents, evaluate results, and merge the winner.

Runs a multi-phase verification pipeline including build, type-check, lint, tests, security scan, and diff review to ensure code quality before creating a PR.

Tracks bidirectional confidence scores across five domains (TECH, OPS, JUDGMENT, COMMS, ORCH) for agents and users, with triggers, anti-patterns, and pool scoring per runtime.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.

Evaluates execution transcripts and output files against a list of expectations, assigning pass/fail verdicts with cited evidence and critiquing the assertions themselves.

Compares coding agents head-to-head on reproducible tasks, measuring pass rate, cost, time, and consistency.

Runs a multi-agent adversarial verification loop where two independent reviewers must both pass before output ships, with a fix cycle for convergence.

Measures whether coding agents actually follow skills, rules, or agent definitions by generating test scenarios, running agents, and classifying tool calls to report compliance rates.