/goal condition with separate evaluator
Set the check as a /goal condition: a separate evaluator re-checks it after every turn and the agent keeps working until the goal resolves.
proof: tests run count blocks: agent stops before checks pass
Source
https://code.claude.com/docs/en/best-practicesChecked 2026-10-16. Read the original before installing.
By harness
| Harness | Status | How |
|---|---|---|
| Cursor | unsupported | No equivalent; use stop follow-up loop. |
| Claude Code | native | /goal |
| Grok Build | unsupported | No equivalent documented. |
| Codex | unsupported | No equivalent documented. |
| AGENTS.md generic | unsupported | Harness feature. |
By model family
| Claude | source |
| GPT | n/a |
| Grok | n/a |
| Gemini | n/a |
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.