by alex-durango
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.
# Add to your Claude Code skills
git clone https://github.com/alex-durango/pingfusiLast scanned: 7/25/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-07-25T06:21:09.787Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}pingfusi is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by alex-durango. 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. It has 101 GitHub stars.
Yes. pingfusi passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/alex-durango/pingfusi" and add it to your Claude Code skills directory (see the Installation section above).
pingfusi is primarily written in JavaScript. It is open-source under alex-durango on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh pingfusi against similar tools.
No comments yet. Be the first to share your thoughts!
pingfusi is an MCP that lets AI agents call human reviewers.
Think MTurk for AI agents. With pingfusi your agent can:
Set up Pingfusi for your coding agents with a single command.
npx pingfusi setup
Here are some example prompts you can try with the pingfusi MCP.
| feedback about | example prompt | what you get | demo |
|---|---|---|---|
| playtest | get 3 playtesters on mygame.itch.io/demo. use pingfusi |
a playtest report from real players | https://pingfusi.com/playtest |
| a confusing page | Is my pricing page confusing anywhere? use pingfusi |
comments pinned to what's off | |
| a website clone | Clone www.example.com pixel-perfect. use pingfusi |
a perfectly cloned website | copy-anything.com |
| design taste | Make my website not look like AI slop. use pingfusi |
design feedback | video |
| video vibes | Does my promo video look right? use pingfusi |
feedback pinned to timestamps |
Each of these publishes the work first so the reviewer can open it; when in doubt, publish: a reviewer can only judge what they can see. Text-only questions work too — if words can carry the whole question, the reviewer just sees the question.
Every job is the same loop underneath:
Example: you ask for a landing page that doesn't look like AI slop. The agent publishes it, a reviewer answers "gradient looks template-y" and "too much padding under the hero". The agent fixes both and refiles; the next reviewer approves. You come back to a page a human signed off on.
The full command lives in docs/COMMANDS.md.
pingfusi setup install + onboarding
pingfusi doctor check the install; prints a fix per problem
pingfusi ask "<question>" ask a human reviewer, from any directory
pingfusi studio [ping_id] local viewer for playtest & review results —
sessions, recordings, transcripts, agent findings
MIT