Schedule agents to open small cleanup pull requests for review

Encode golden principles, then let background agents scan, grade and open targeted refactors.

Prompt

Evaluate and apply this CI technique to my repository: Schedule agents to open small cleanup pull requests for review.

Encode golden principles, then let background agents scan, grade and open targeted refactors.

Read the technique and its source-backed company examples: https://starsling.dev/ci-playbooks/techniques/scheduled-cleanup-prs.md

Inspect this repository’s CI workflows, build and test commands, dependencies, and recent run timings. Identify where this technique applies and explain the expected benefit using this repository’s evidence.
Measure a baseline from recent comparable runs: elapsed time, queue time, runner minutes and failures where available. If data is unavailable, say what cannot be measured.
Compare relevant company approaches, checking prerequisites, platform differences and tradeoffs. Rank applicable options by evidence, fit and measurable opportunity; do not present company results as predictions for this repo.
Recommend the smallest safe change, show what checks and fallback paths remain, and ASK ME WHICH CHANGE TO APPROVE BEFORE EDITING ANY FILES.
Only after approval, work on a new feature branch, make one reversible change, and open a reviewable pull request. Never merge or push to a default or protected branch.
Keep required checks, test coverage, deployment and release behavior intact. Validate the change and compare equivalent runs where possible; report limitations and what should be monitored after merge.

View all playbooks

How OpenAI used this technique

Read what OpenAI changed and follow the original sources.

Schedule agents to open small cleanup pull requests for review

OpenAI's agent-first team encodes golden principles in the repository, such as preferring shared utility packages and validating data at its boundaries. On a regular cadence, background agents scan for deviations, update quality grades and open targeted refactoring pull requests, and most of them can be reviewed in under a minute and automerged. This replaced a weekly manual cleanup.

Our team used to spend every Friday (20% of the week) cleaning up “AI slop.” Source

Use it when: Cleanup work piles up until it needs a dedicated day.
Before applying it: Automerge only changes small enough to review in a minute and covered by required checks.

How OpenAI used this technique

Schedule agents to open small cleanup pull requests for review

Company Playbooks