human-in-the-loop Eval report.

Task wording matches this skill metadata.

• Evaluate human-in-the-loop before installing it in an agent workflow
• research
• Research agents workflows; Claude Code teams; builders willing to evaluate younger projects

Install handoff is available.

• npx skills add mvschwarz/openrig --skill human-in-the-loop

standard package or runtime install path

• npx skills add mvschwarz/openrig --skill human-in-the-loop

Good trust signals with a few areas worth checking before rollout.

• Strong shortlist
• 481 GitHub stars
• Apache-2.0

Needs review

• Permission surface may require sandboxing

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

• Test manually in an isolated workspace and compare against safer alternatives.
• High-risk permission hints: Secrets or environment access

Apache-2.0

• Apache-2.0

secrets or environment access, filesystem or document access

• Network access: medium
• Filesystem access: medium
• Secrets or environment access: high