The four-settings loop template: a separate verifier model that never shares context with the writer, a hard stop rule, a state file re-read each cycle, and worktree isolation. Point it at a checkable backlog and let it run overnight.
GOAL: every test in [/tests/TARGET] passes, lint is clean, zero type errors.
EACH CYCLE:
1. run the suite, read every failure
2. pick the single highest-impact failure
3. write the smallest change that fixes it
4. re-run tests + lint + type check
VERIFY: a separate model instance checks the goal — never the writer. Verifier prompt: "You are a verifier. You did not write this code. GOAL: <the exact goal string>. Given the diff and the test output, answer ONLY: PASS — every condition in GOAL is objectively met, with evidence, or FAIL: <the specific condition not met, and the evidence>. Do not fix anything. If unsure, FAIL."
STOP WHEN: verify passes, OR after 10 iterations, OR $5 spent, OR no progress in 2 attempts.
ON BLOCKER: log it, skip to the next item, never halt the whole loop.
STATE: append done / failed / next to a state file, re-read it at the top of every cycle.
ISOLATION: one git worktree per subagent.
claude-code
Implementation note
Near-verbatim from the source article's copy-paste template (structure and verifier prompt verbatim; target path parameterized). The verifier-never-shares-context split is the load-bearing setting: the writer is optimistic, the verifier is skeptical. Source claims ~340 cycles/7 days at ~$2.30 per accepted change; treat the numbers as anecdote, the shape as sound.
/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
/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