{
  "id": 15554540,
  "title": "OpenRouter's Armor Vets Agent Tool Calls. In Claude Code Mode It Only Flags Them",
  "url": "https://urgent.news/2026/10/19/openrouters-armor-vets-agent-tool-calls-in-claude-code-mode-it-only",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-19T04:01:37.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/gabrielanhaia/openrouters-armor-vets-agent-tool-calls-in-claude-code-mode-it-only-flags-them-5eno"
  },
  "original_language": "en",
  "account": "OpenRouter launched Armor in beta to act as a safety classifier between AI models and applications. The tool checks every tool call against user-defined rules written in plain English before execution. When a call is flagged, the model is informed of the rule it violated and the call is not executed. In Claude Code mode, Armor flags the tool_use but keeps it in the response, marking it instead of stopping it. This allows the application to decide whether to halt the call based on the flagged verdict. The safety classifier uses a decision model called TypeSafe's Jev, which evaluates the call against the provided rules and returns a probability indicating whether it matches each rule. Jev is designed to provide more precise results than traditional regex-based filtering methods. There are three types of rules: hard_deny, soft_deny, and allow. Hard_deny rules block the call without exceptions, soft_deny rules block the call unless an allow rule matches or the user explicitly requests the operation, and allow rules define exceptions to soft_deny rules. Each rule has an id, optional name, instructions, and optional threshold values, with default values of 0.6 for deny rules and 0.7 for allow rules. OpenRouter offers an audit mode, allowing developers to test and tune their rules using real traffic before enforcing them. In audit mode, Armor scores every call but does not block them, enabling developers to monitor and adjust their rules as needed.",
  "summary": "Book: System Design Pocket Guide: Fundamentals Also by me: Thinking in Go (2-book series) — Complete Guide to Go Programming + Hexagonal Architecture in Go My project: Hermes IDE | GitHub — an IDE for developers who ship with Claude Code and other AI coding tools Me: xgabriel.com | GitHub Your agent decides to delete a folder you never mentioned. Somewhere between the model and your shell,…",
  "key_points": [
    "Armor is a safety classifier tool for AI model tool calls",
    "In Claude Code mode, Armor flags tooluse but allows execution",
    "Armor uses TypeSafe's Jev model for precise rule evaluation"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}