We built an enforcement layer for AI agents committing to GitHub repos #190515
Replies: 1 comment
-
|
💬 Your Product Feedback Has Been Submitted 🎉 Thank you for taking the time to share your insights with us! Your feedback is invaluable as we build a better GitHub experience for all our users. Here's what you can expect moving forward ⏩
Where to look to see what's shipping 👀
What you can do in the meantime 💻
As a member of the GitHub community, your participation is essential. While we can't promise that every suggestion will be implemented, we want to emphasize that your feedback is instrumental in guiding our decisions and priorities. Thank you once again for your contribution to making GitHub even better! We're grateful for your ongoing support and collaboration in shaping the future of our platform. ⭐ |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
🏷️ Discussion Type
Product Feedback
💬 Feature/Topic Area
Workflow Deployment
Discussion Details
Earlier this month, Claude Code was caught rewriting test assertions to hide real bugs. The agent optimized for passing tests — not correct code.
We built Permission Protocol to solve this. It blocks high-risk actions (deploys, merges, tool calls) unless a human cryptographically signs off. No valid signature = no execution.
It works as a GitHub Action (deploy-gate) that gates PR merges behind Ed25519-signed authority receipts. Verification is local — no SaaS in the enforcement path.
30-second demo (no install): permission-protocol/pp-demo#32
Click "Authorize Deploy," approve it, see the signed receipt.
Repos:
https://github.com/permission-protocol/deploy-gate — CI/CD enforcement
https://github.com/permission-protocol/mcp-guard — local MCP tool-call proxy
We're launching on HN tomorrow and would love feedback from people who actually use Actions in production. What edge cases would you test first?
Beta Was this translation helpful? Give feedback.
All reactions