# A cost fix that cuts coverage changes what the job does

I split token fixes by what they can break instead of what they save.

By Ki Moon · 2026-08-26 · technique · current
Canonical: https://kihmoon.com/bench-notes/p/cost-fix-scope-decision/

**Symptom:** A job's token use dropped after an efficiency pass, and its output count dropped with it.

My token-waste review proposes fixes. At first every fix waited for my approval, and approving every fix trains me to stamp them. Skipping approval lets an efficiency change quietly change what a job does.

On one review, 2 of the 8 proposed fixes looked like savings and were really changes to what the job covered.

In a second case, a rewrite of a nightly enrichment job used about a fifteenth of the old version's tokens on one run.

It also found about a third fewer people than the old version, and that count, not the token count, decides whether such a rewrite ships.

The lost people sat on older email threads that had been re-ingested. Their activity dates fell outside the window the cheaper query filtered on. The job feeds the CRM, so the saving meant fewer records reached it.

So fixes now split by blast radius, and the split decides whether I look before a fix lands.

For auto-applied fixes, a clean record on work written minutes earlier is the easy case. It says little about older work, or someone else's. When an auto-applied fix turns out wrong, shrink the auto-apply list rather than going back to asking on everything.

## Check your setup (read-only)

List the jobs whose git log shows a cost cut in the last 90 days. Read each job's run log. Compare its output and input counts for the week before and the week after the cut. Any output drop the inputs don't explain means the cut reduced coverage, and that's a gap.

**Passes if:** Output counts after the cut move with input counts, inside the job's usual week-to-week range.

**Access needed:** scheduler, local-config

## If it fails (changes to make later, not part of the check)

1. Apply behaviour-preserving fixes without asking. Behaviour-preserving fixes include deduplicated prompt text, prompt caching, and a pointer instead of a restated doc. Output bounds that don't truncate results are also behaviour-preserving.
2. Ask before any fix that changes coverage. Coverage fixes include kill criteria, abort thresholds and dropped inputs. Coverage fixes also include a collapsed or serialized fan-out and batching units into fewer agents.
3. Ask before downgrading the model on a stage that needs judgment.
4. Compare output counts before and after every cost fix, not only tokens.
5. Report every applied fix with its checklist number, even when nothing needed approval.

**Applies if:** Your git log shows a cost cut to a job that writes CRM records or feeds a list.

**Skip if:** Your git log shows no cost cut to any job that writes records or feeds a list.

Tags: cost, approval, agents
