Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a claim, memory write, or action is trusted.
Latest release v1.1.1 · 19 Oct 2026
5 files for Codex, OpenCode and GitHub Copilot: huqan AGENTS.md, huqan copilot-instructions.md, huqan actions.instructions.md, huqan security.instructions.md and 1 more — 3,605 tokens loaded in every session.
AGENTS.md C 2,818 tok .github/copilot-instructions.md A 291 tok .github/instructions/actions.instructions.md A 165 tok .github/instructions/security.instructions.md A 200 tok .github/instructions/tests.instructions.md A 131 tok These files are ali-ulu/huqan's own configuration — they tell Codex, OpenCode and GitHub Copilot how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.