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.
/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 A · 90/100 — how grades work →
More testing loops
Ralph a test backlog
Iterate over a prioritized list of untested modules with fresh context each pass, writing real behavioral tests for one module at a time and banking lessons in a guardrails file.
/loop each iteration with fresh context: read .ralph/test-backlog.json and .ralph/guardrails.md, pick the top unfinished module, write behavioral tests for its public API (no snapshot-only tests), run the suite, and mark the module done only when its tests pass and coverage for it exceeds 80%; append any discovered testing gotcha (fixtures, mocking rules, async traps) to .ralph/guardrails.md; stop when the backlog is empty or after 25 turns
Test all endpoints
Run tests against every API endpoint until coverage is complete or you hit 30 iterations.
/goal all endpoints tested or stop after 30 turns
Ship avatar endpoint to spec
Build and test a new /users/:id/avatar route until it passes tests, lint, and matches the OpenAPI schema.
/goal until grep -q "users/:id/avatar" src/routes/users.ts AND pnpm test -- tests/integration/users.avatar.spec.ts passes AND grep -q "/users/{id}/avatar" openapi.yaml AND pnpm lint passes, or stop after 15 turns