Canonical: https://botbento.com/usecases/review-agent-written-pull-requests-against-quality/
Format: Markdown representation of the public HTML page.

# Review agent-written pull requests against quality gates

[Coding](https://botbento.com/usecases/coding/) · Intermediate

Check machine-generated diffs for tests, style and structural fit

A review bot that inspects code contributions produced by coding agents before they reach a shared branch. It runs the project's checks, reads the diff against existing conventions, looks for missing tests and risky edits, and drafts review notes so a person can decide what merges. The bot keeps the same quality steps in place even when output volume rises.

## Quick answers

**What does it do?** Check machine-generated diffs for tests, style and structural fit. Result: Draft review notes for approval.

**What does it need?** Tools: GitHub, Terminal, Docs. Intermediate: some setup. The prompt includes an approval step.

**How do I run it?** When something happens: New pull request arrives. Copy the prompt below into a bot in BotBento.

## How it works

1. When something happens: New pull request arrives
2. Then: Run checks and read the diff
3. Result: Draft review notes for approval

## Prompt to start with

```text
When a pull request appears, read the diff and the surrounding files it touches. Run the repository's lint, formatting and test commands and record what passed or failed. Flag changes with no accompanying tests, edits that break the module's existing structure, and anything that looks like unrelated scope creep. Write concrete review comments pointing at the lines involved. Post nothing on its own: prepare the review as a draft and wait for the user's approval before submitting comments or requesting changes. Never merge, close or delete branches without explicit approval.
```

## Tools it uses

GitHub, Terminal, Docs

## Works with

BotBento

## Tags

code-review, quality, agents, testing

## Source

[I Read the Clankers' Code](https://news.ycombinator.com/item?id=50340362) — Hacker News · checked 2026-11-13

Summarized in our own words. Any results described there are the authors’ own, not measured by BotBento.

Verified 2026-11-13: passed every automated gate and a second-model review (kimi-code/k3.1-pro). Automated, not human review. [How verification works](https://botbento.com/usecases/verification/)

By BotBento Editorial · Added 2026-11-13 · Updated 2026-11-13 · [Suggest a correction](https://botbento.com/contact/)

## Related use cases

- [Review large AI-generated code diffs before merge](https://botbento.com/usecases/review-large-ai-generated-code-diffs-before/) — Refactor and walk through big diffs, then draft a clean commit
- [Automated issue resolution and pull request creation](https://botbento.com/usecases/automated-issue-resolution-and-pull-request-creation/) — Turn backlog tickets into tested pull requests using isolated execution environments
- [Fix bugs from issue reports with tests](https://botbento.com/usecases/automated-test-driven-bug-fixing-and-pull/) — Reproduce an issue, write a failing test, patch the code, and prepare a PR for review
