Loading ToolBench
AI coding agents can't quietly fake "done". Signed ed25519 receipts prove the gates actually ran — bound to the commit, verifiable offline. Fail-closed hooks block the edit, not the PR. Harness engineering over Claude Code, Cursor, Codex, Qwen, OpenCode.
Scoring was not performed
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 27 | 2026-07-28+ | v2 |