grade-iterate

Use when a launched managed agent needs grading against a rubric and improving ('grade my agent', 'is it good enough'). Builds the outcome with outcome_builder.py, reads verdicts with verdict_reader.py and runs held-back evals from eval_scaffold.py.

Install

KitScout test notes

Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.

Similar tools

• ask-matt 323,485 ★
  Ask which skill or flow fits your situation. A router over the skills in this repo.
• chief-of-staff 323,485 ★
  Pursue a long-running goal in a single session by co-ordinating subagents.
• claude-handoff 323,485 ★
  Hand the current conversation off to a fresh background agent that picks up the work immediately.
• grill-me 323,485 ★
  A relentless interview to sharpen a plan or design.
• grilling 323,485 ★
  Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thin