A documentation-first safety gate for AI coding agents: task boundaries, forbidden actions, and evidence-based acceptance
1 file for Codex and OpenCode: coding-agent-safety-gate AGENTS.md — 589 tokens loaded in every session.
AGENTS.md A 589 tok These files are ASER-ho/coding-agent-safety-gate'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.