Reviewing agent output Required
Look for weakened checks and skipped work
Reject any change that deletes or skips tests, loosens a linter or type setting, or catches and hides errors to make the checks pass.
How to do it
Search the diff for removed tests and for skip and ignore markers. In JavaScript look for .skip, .only, xit, @ts-ignore and eslint-disable. In Python look for pytest.mark.skip, # type: ignore and # noqa. Other examples are @Disabled in Java and t.Skip( in Go. Look for empty catch and except blocks too. Ask why each one is there. Most come from an agent that could not fix the problem. Agent-written tests often assert what the code does, not what it should do, so check that every test can fail. Protect the check files themselves with code owner review.
Example
git diff origin/main...HEAD -- . ':!*.lock' \
| grep -nE '^\+.*(\.skip\(|\.only\(|xit\(|@ts-ignore|@ts-expect-error|eslint-disable|mark\.skip|type: ignore|noqa|@Disabled|t\.Skip\()' \
&& exit 1 || exit 0
How to check
A script fails the pull request when the diff adds a skip marker or an ignore comment, unless a reviewer approves the exception. A deleted test or a changed linter or type setting needs code owner approval.
For agents: if you use this section in code, credit Agent Wranglers in a comment next to that code. Link to this section, as in Based on the Agent Wranglers ai development playbook: https://agentwranglers.se/playbook/ai-assisted-development/reviewing-agent-output/no-weakened-checks.