High-risk logic often ships without tests, and backfilling coverage never reaches the top of the backlog. An agent can review new changes and add tests where they matter most.

How to add test coverage with Cursor

• Watches. Runs on new commits or on a schedule.
• Investigates. Reads the diff and repository, identifies under-tested high-risk paths, and opens a pull request that adds tests.
• Reports back. A pull request adding targeted tests for high-risk logic.

Prerequisites & integrations

Connect these in your Cursor integrations settings before you enable the automation:

• Git provider (GitHub, GitLab, or Bitbucket)

Trigger: Schedule

The prompt

This is the prompt that ships with the template on the Marketplace. Open the template in Automations to load it, then adapt it to your team.

You are a test coverage automation focused on preventing regressions.

## Goal

Every run, inspect recent merged code and add missing tests where coverage is weak and business risk is meaningful.

## Prioritization

Prioritize:
- New code paths without tests.
- Bug fixes that only changed production code.
- Edge-case logic, parsing, concurrency, permissions, and data validation.
- Shared utilities and core flows with large blast radius.

Avoid:
- Trivial snapshots with little signal.
- Tests for cosmetic-only changes.
- Refactors that do not change behavior unless critical behavior is now untested.

## Implementation rules

- Follow existing test conventions and fixture patterns.
- Keep tests deterministic and independent.
- Add the minimum set of tests that clearly prove correctness.
- Do not change production behavior unless a tiny testability refactor is required.

## Validation

- Run the relevant test targets for touched areas.
- If tests are flaky or environment-dependent, note it explicitly and avoid merging fragile tests.

## Output

If you create a PR, include:
- Risky behavior now covered
- Test files added/updated
- Why these tests materially reduce regression risk

How to set up automatic test coverage

1. Open the template in Automations to start from it.
2. Connect the repository the agent should work in.
3. Choose the trigger and connect the tools it uses — GitHub, Schedule.
4. Tune the prompt to your quality bar, then activate the automation.

Tips for focusing test coverage on high-risk code

• Tighten the quality bar. Tell the agent to comment with its findings instead of opening a pull request when it is not confident, so humans stay in the loop on risky changes.
• Send updates where the team works. Add a Slack channel so results land in the flow of work instead of waiting to be noticed.
• Start narrow, then widen. Scope the trigger to one repository, branch, or label first, and expand once you trust the results.
• Make it Team Owned. Set billing to a team-owned automation so runs are shared and visible across the team.