Show evidence, don't assert success
Best-practice rule: have the agent show the test output, the command it ran and what it returned, or a screenshot, instead of saying it works.
proof: logsproof: screenshotproof: tests run count blocks: claims done without running checks
Source
https://code.claude.com/docs/en/best-practicesChecked 2026-10-16. Read the original before installing.
By harness
| Harness | Status | How |
|---|---|---|
| Cursor | adapted | Put it in an alwaysApply .cursor/rules file. Untested. |
| Claude Code | native | CLAUDE.md line. |
| Grok Build | adapted | Grok reads CLAUDE.md and AGENTS.md (docs.x.ai). |
| Codex | adapted | AGENTS.md line. |
| AGENTS.md generic | adapted | AGENTS.md line. |
By model family
| Claude | source |
| GPT | untested |
| Grok | untested |
| Gemini | untested |
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.