---
title: "Have an agent prove code is unused, then delete it in reviewed batches"
description: "Fan out one deletion pull request per area, with the agent's evidence in each description."
url: https://starsling.dev/ci-playbooks/techniques/agent-dead-code-sweep
canonicalUrl: https://starsling.dev/ci-playbooks/techniques/agent-dead-code-sweep
---

# Have an agent prove code is unused, then delete it in reviewed batches

Fan out one deletion pull request per area, with the agent's evidence in each description.

## How to choose an approach

This technique currently has one documented company example. Validate its prerequisites, tradeoffs and original CI environment against your repository before adapting it.

- **[OpenAI](https://starsling.dev/ci-playbooks/openai#agent-dead-code-sweep)**: Use it when Unused tests, snapshots, images and code add CI time and artifact size. Check before adopting: Past incidents came from mistaken removals, so require the agent to cite its evidence for each deletion and send each pull request to the team that owns the code.

## Apply this technique

````text
Evaluate and apply this CI technique to my repository: Have an agent prove code is unused, then delete it in reviewed batches.

Fan out one deletion pull request per area, with the agent's evidence in each description.

Read the technique and its source-backed company examples: https://starsling.dev/ci-playbooks/techniques/agent-dead-code-sweep.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.
````

## How OpenAI used this technique

Read what OpenAI changed and follow the original sources.

### OpenAI: Have an agent prove code is unused, then delete it in reviewed batches

OpenAI engineers gave GPT-6 Astra a short prompt to find and clean up dead code, with Slack, the feature-flag platform and other sources allowed as evidence. It looked at past pull requests, Slack threads, project trackers and production profiling tables, and explained its rationale for each deletion. Five engineers ran variations of the prompt across repositories and fanned the code reviews out to the teams with context on each project.

Evidence: Company-reported result or observation

another set of cleanups removed about 400 visual snapshot variants from our test suite ([Source](https://developers.openai.com/blog/maintaining-software-with-the-gpt-6-family))

Use it when: Unused tests, snapshots, images and code add CI time and artifact size.

Before applying it: Past incidents came from mistaken removals, so require the agent to cite its evidence for each deletion and send each pull request to the team that owns the code.

[Read more in the OpenAI playbook](https://starsling.dev/ci-playbooks/openai#agent-dead-code-sweep)

[Primary source](https://developers.openai.com/blog/maintaining-software-with-the-gpt-6-family)

## CI optimization is continuous work.

Apply this technique yourself, or use StarSling Runners for faster GitHub Actions and optional agent-driven optimization PRs, which teams on eligible paid plans can turn on.

[Get self-improving CI](https://starsling.dev/products/runners)

## Company Playbooks

### [Anthropic](https://starsling.dev/ci-playbooks/anthropic)

Run only affected tests

### [DoorDash](https://starsling.dev/ci-playbooks/doordash)

Run build and test in parallel, sharded across CI agents

### [Linear](https://starsling.dev/ci-playbooks/linear)

Benchmark the same job on faster hardware

### [Mastra](https://starsling.dev/ci-playbooks/mastra)

StarSling runners for the slowest test workflow

### [OpenAI](https://starsling.dev/ci-playbooks/openai)

Rank CI fixes by the minutes they save

### [Ramp](https://starsling.dev/ci-playbooks/ramp)

Move a CPU-bound test suite to a faster CPU

### [Shopify](https://starsling.dev/ci-playbooks/shopify)

Let an agent iterate against one CI metric

### [Spotify](https://starsling.dev/ci-playbooks/spotify)

Build arm64 on native arm64 runners

### [Stripe](https://starsling.dev/ci-playbooks/stripe)

Run only the tests a change can reach

### [Uber](https://starsling.dev/ci-playbooks/uber)

Build the merge-queue speculations most likely to be needed