What it does
The agent runs a project's test suite, reads the failing implementation and test files, and works out the root cause of each failure. Its output is a structured diagnosis that lists the location of each failure, the likely cause and a recommended fix. It does not change code or tests. The user or another agent applies the fix and reruns the tests to verify it.
It suits two situations: after a feature has been implemented or a bug fixed, to confirm that nothing has broken, and when a local or CI test run has failed and needs triage rather than a repeated run. In triage, it separates implementation bugs from faulty tests and can check whether an intermittent failure reproduces consistently, under CI-only conditions, or not at all, so that a flaky test is not skipped without evidence.
Running it requires a project with a test suite that can be executed, along with its configuration. The agent first identifies the test runner and config, executes the suite (the examples in the source mention coverage reporting), and then reads the relevant code. For intermittent failures it may rerun a single test several times and review CI logs.
Limitations and requirements
The agent never edits code or tests. Fixes must be applied by the user or another agent, which then needs to re-run the tests to verify them.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 938
test-runner
Executes a project's test suite, analyzes failures, and diagnoses root causes with concrete fix recommendations. This agent never edits code or tests itself — it runs tests, reads the failing code and test files, and hands back a structured diagnosis for the user or another agent to apply and re-verify. Use PROACTIVELY after implementing a feature or fixing a bug, and whenever a test run (local or CI) comes back red and needs root-cause triage rather than a blind rerun. <example> Context: A developer just finished implementing a new feature and wants to confirm nothing broke before opening a
As shown on www.aitmpl.com when we last read it