The governance layer for AI agents — monitor reasoning, audit tool calls, and secure the loop through OHTTP privacy routing.
1 file for Codex and OpenCode: claw-shield AGENTS.md — 2,046 tokens loaded in every session.
AGENTS.md C 2,046 tok These files are xinxin7/claw-shield's own configuration — they tell Codex and OpenCode 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.