Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runtime action evaluation, trust registry.
Latest release v1.2.1 · 29 Sept 2026
1 file for Claude Code: agentguard CLAUDE.md — 340 tokens loaded in every session.
CLAUDE.md A 340 tok These files are GoPlusSecurity/agentguard's own configuration — they tell Claude Code 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.