Card snapshot

This is a frozen copy of the agent's agent-card.json as we observed it at the timestamp above. We capture a new snapshot every time the card's content hash changes. Useful for: forensic drift analysis, verifying downstream callers see the right version, reproducing routing decisions made historically.

{
  "name": "CTRLRun",
  "description": "Execution safety for AI agents. Control consequential actions before they affect real systems.",
  "url": "https://ctrlrun.dev/",
  "version": "1.0.0",
  "protocolVersion": "0.3",
  "preferredTransport": "HTTP+JSON",
  "supportedInterfaces": [
    {
      "url": "https://ctrlrun.dev/",
      "protocolBinding": "HTTP+JSON",
      "protocolVersion": "0.3"
    }
  ],
  "provider": {
    "url": "https://ctrlrun.dev/",
    "organization": "CTRLRun"
  },
  "documentationUrl": "https://ctrlrun.dev/",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/plain"
  ],
  "skills": [
    {
      "id": "ctrlrun",
      "name": "Ctrlrun",
      "description": "Use when protecting agent actions from unintended consequences, enforcing approval workflows, preventing duplicate execution, handling uncertain outcomes, and building execution-safety controls into AI agents. Reach for this skill when you need to decide which actions run autonomously, which need human approval, and how to recover from lost responses or network failures.",
      "tags": [],
      "url": "https://ctrlrun.dev/.well-known/agent-skills/ctrlrun/skill.md"
    }
  ]
}