@moltzap/cc-judge
TypeScript CLI + SDK for planned Claude Code harness runs, LLM bundle judging, and summary.md + results.jsonl reports with Braintrust + Promptfoo telemetry.
3
Versions
MIT
License
No
Install Scripts
Verified
Provenance
Supply chain provenance
Status for the latest visible version.
SLSA provenance attestation
npm registry signatures
gitHead linked
Maintainers
tapanc
Keywords
claudeclaude-codeevalsagentllm-judgetypescript
Accepted risks
Findings the reviewer chose to accept rather than block on.
| Source | Rule | Reason | Accepted by | When |
|---|---|---|---|---|
| provenance | publisher-changed | AI (provenance): Transition to GitHub Actions CI publishing is confirmed by SLSA provenance attestation; consistent with legitimate automation setup. | ai | |
| phantom-deps | phantom-dep:@effect/platform | AI (phantom-deps): @effect/platform is a peer/transitive dep in the Effect ecosystem; commonly declared but used indirectly via @effect/platform-node. | ai | |
| phantom-deps | phantom-dep:zod | AI (phantom-deps): zod is declared in dependencies; phantom-dep heuristic fires but it's used as a runtime dep in this SDK. | ai |