Get the fix to score 90+
Run verify commands and benchmark checks until the target code scores 90 or higher on the benchmark, stopping after 5 attempts.
Prompt
/goal the transcript reports a line matching SCORE: <n>/100 (threshold: 90, gate: pr) with n >= 90 for <slug> on branch <branch>, after <(bugfix) the REPRODUCE test is shown failing on unfixed code and passing on the final code, and> <verify commands, comma-separated> <(hot-path) and make bench-compare> all pass on the final code, or stop after 5 fix rounds
claude-code
Source: maroffo ↗graded C · 68/100 — how grades work (Safety Score v2) →
Similar loops
All testing loops →C
/goalTestingmedium risknew
Fix the flaky checkout test
Run checkout tests repeatedly until 20 consecutive passes, logging failure modes and hypotheses after each iteration.
/goal Reproduce and fix the flaky checkout test so it passes 20 consecutive runs, verified by npm test -- checkout, while preserving checkout API behavior and existing correctness tests. Use the checkout test files, checkout service code, fixtures, and related logs. Between iterations, record the observed failure mode, hypothesis, change, and rerun result. If reproduction stays unavailable or valid paths are exhausted, stop with reproduction attempts, logs, most likely absent condition, blocker, and next input needed
C
/goalTestingmedium risknew
Fix flaky tests, get CI green
Run an agent to identify and fix flaky tests until your CI pipeline passes completely.
/goal fix all flaky tests and make CI green in a new chat. Pair it with a custom mode to follow a playbook, or /loop for recurring check-ins
C
/goalTestingmedium risk
Reach a coverage target
Add focused tests for the least-covered files and re-measure each turn until coverage hits 80 percent or the turn cap.
/goal test coverage is at least 80% with all tests passing — add focused tests for the least-covered files, re-run coverage each turn, stop at the threshold or after 12 turns