#agent-safety

Auxfirst Skill Global

Score every action an AI agent can take, cap its autonomy at the hottest dimension, and ship the mandate, exceptions and owner's manual behi...

Axiom

Safety-first workflow routing for Codex and Claude Code: explicit scope, authorization, evidence, and rollback for high-impact agent actions...

Task Compass Skill

Task Compass Skill: deterministic, auditable task routing for AI agents and OpenClaw

Gensee Crate: AI Agent Runtime Safety

Runtime safety for AI coding agents with real-time enforcement, system-event monitoring, and long-horizon provenance. Supports Claude Code,...

Unwind

Deterministic security engine for AI agents. See, block, rewind, prove.

Guard

Runtime guardrails for TypeScript AI agents. Prevents duplicate tool calls, enforces per-user cost budgets, and gates irreversible actions....

Cycles Docs

Documentation for Cycles — AI agent governance, runtime budget, action authority, MCP integration

Agent47

Your AI agent just burned $200. AgentGuard stops it at $5. Runtime cost guardrails for AI agents — budget enforcement, loop detection, kill...

Intaris

Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in...

SafeAgent

Execution control layer for AI agents — prevents duplicate or incorrect real-world actions under retries, uncertainty, and stale context.

BridgeWard

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, ref...