Guardrails for AI coding agents — block catastrophic tool calls before they run. Semantic, agent-neutral, near-zero false positives.
Latest release v1.4.0 · 3 Aug 2026
1 file for Claude Code: fence CLAUDE.md — 1,815 tokens loaded in every session.
CLAUDE.md A 1,815 tok These files are hoophq/fence'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.