AI article
OpenRouter's Armor Vets Agent Tool Calls. In Claude Code Mode It Only Flags Them
Community description: OpenRouter's Armor beta checks each agent tool call against plain-English rules. In its Claude Code mode, a flagged call still reaches your client.
Dev.to | Oct 19, 2026 | Gabriel Anhaia
Automated excerpt
For each tool call, OpenRouter sends the call, your rules and the conversation to a decision model, which returns a probability that the call matches each rule (Armor docs). That setting doesn't reach the Claude Code mode. Claude Code requests are released with an unavailable verdict instead, and Claude Code falls back to its own local auto-mode check.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.