pingfusi
Reduces costly agent iterations and prevents merged defects by embedding human review checkpoints within AI-assisted development workflows, enabling faster f…
MCP server + CLI that puts a real human in your coding agent's loop. It publishes work mid-task, a reviewer pins what's wrong and returns a verdict, and the agent iterates until approved.
- Ask Claude to pause code changes for human review before committing to main branch.
- Generate pull request drafts and get team feedback in the agent's loop automatically.
- Automate code iteration cycles by having reviewers pin issues for Claude to fix.
Reduces costly agent iterations and prevents merged defects by embedding human review checkpoints within AI-assisted development workflows, enabling faster feedback cycles without sacrificing code quality.
Engineering teams using AI coding agents who need asynchronous human oversight before task completion.
https://github.com/alex-durango/pingfusi
By alex-durango
How to Get It
claude plugins install alex-durango/pingfusi
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Pause code changes for human review before committing to main branch
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 109 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 109 GitHub stars; contributors unknown; last commit 0d ago; license MIT.