Ai Safety AI Agent Skills

Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases. Produces CGD (Clarity-Gated Documents) and validates SOT (Source of Truth) files.

"Code -> audit -> amend -> audit again -> pass." Blind Auditor is a mandatory code auditing system built on the MCP (Model Context Protocol). It uses a unique "Thinking Isolation" mechanism to force AI Agents to enter an independent "audit phase" and self-review their code before outputting the final result. Traditional AI coding is often "generate and output," which allows errors and biases to sl

⭐ Like this project? Please star the repository on GitHub to show your support and stay updated! ⭐ Modern AI-powered coding assistants (like Cursor, Cline, Roo Code, etc.) excel at understanding code structure and syntax but often struggle with the specifics of rapidly evolving libraries and frameworks, especially in ecosystems like Rust where crates are updated frequently. Their training data cut

iptables for MCP. Blocks dangerous tool calls, scans for secret leakage, logs everything. No AI, no cloud, pure rules. Sits between your AI coding tool (Claude Code, Cursor, Windsurf) and MCP servers, intercepting every JSON-RPC message and enforcing YAML-defined policies. MCP servers have full access to your filesystem, shell, databases, and APIs. When an AI agent calls tools/call, the server exe

CSL-Core (Chimera Specification Language) is a deterministic safety layer for AI agents. Write rules in .csl files, verify them mathematically with Z3, enforce them at runtime — outside the model. The LLM never sees the rules. It simply cannot violate them. Originally built for Project Chimera, now open-source for any AI system. This doesn't work. LLMs can be prompt-injected, rules are probabilist