batrapulkit/squidbrake
Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.
GitHub repository with 10 stars and 9 forks.
Language: Python
Topics: agent-security, agent-skills, ai-agents, ai-safety, approval-workflow, audit-log, claude-code, claude-code-plugin, codex, cursor