/hub:eval — Evaluate Agent Results
Rank all agent results for a session. Supports metric-based evaluation (run a command), LLM judge (compare diffs), or hybrid.
Usage
What It Does
Metric Mode (eval command configured)
Run the evaluation command in each agent's worktree:
Output:
LLM Judge Mode (no eval command, or --judge flag)
For each agent:
- Get the diff:
git diff {base_branch}...{agent_branch} - Read the agent's result post from
.agenthub/board/results/agent-{i}-result.md - Compare all diffs and rank by:
- Correctness — Does it solve the task?
- Simplicity — Fewer lines changed is better (when equal correctness)
- Quality — Clean execution, good structure, no regressions
Present rankings with justification.
Example LLM judge output for a content task:
Hybrid Mode
- Run metric evaluation first
- If top agents are within 10% of each other, use LLM judge to break ties
- Present both metric and qualitative rankings
After Eval
- Update session state:
- Tell the user:
- Ranked results with winner highlighted
- Next step:
/hub:mergeto merge the winner - Or
/hub:merge {session-id} --agent {winner}to be explicit
