Capture test output with afterShellExecution
afterShellExecution receives the full command and terminal output. Append test runs to an evidence log the reviewer reads instead of the agent's summary.
proof: logsproof: tests run count blocks: narrated results that never ran
By harness
| Harness | Status | How |
|---|---|---|
| Cursor | native | hooks.afterShellExecution with matcher on your test command. |
| Claude Code | adapted | PostToolUse with matcher Bash. |
| Grok Build | adapted | PostToolUse (non-blocking) per docs.x.ai hooks. |
| Codex | untested | Untested. |
| AGENTS.md generic | unsupported | Harness feature. |
By model family
| Claude | any |
| GPT | any |
| Grok | any |
| Gemini | any |
Sponsor slot: your verification tool here, one sponsor per week. Details
Proof of the week
One verification pattern every week, adapted per harness and model. No spam.