[DOCS] Missing required `allowDangerouslySkipPermissions` flag in Agent SDK Overview example

Resolved 💬 2 comments Opened Jan 23, 2026 by coygeek Closed Feb 27, 2026

Documentation Type

Missing documentation (feature not documented)

Documentation Location

https://platform.claude.com/docs/en/agent-sdk/overview

Section/Topic

"Capabilities" section → "Permissions" tab → TypeScript code example

Current Documentation

The TypeScript example under the Permissions tab shows:

import { query } from "@anthropic-ai/claude-agent-sdk";

for await (const message of query({
  prompt: "Review this code for best practices",
  options: {
    allowedTools: ["Read", "Glob", "Grep"],
    permissionMode: "bypassPermissions"
  }
})) {
  if ("result" in message) console.log(message.result);
}

What's Wrong or Missing?

The TypeScript SDK Reference explicitly states that allowDangerouslySkipPermissions: true is required when using permissionMode: 'bypassPermissions':

| allowDangerouslySkipPermissions | boolean | false | Enable bypassing permissions. Required when using permissionMode: 'bypassPermissions' |

The Overview example omits this required flag. Users copying this code will likely encounter a runtime validation error.

Suggested Improvement

Update the TypeScript example to include the required flag:

import { query } from "@anthropic-ai/claude-agent-sdk";

for await (const message of query({
  prompt: "Review this code for best practices",
  options: {
    allowedTools: ["Read", "Glob", "Grep"],
    permissionMode: "bypassPermissions",
    allowDangerouslySkipPermissions: true
  }
})) {
  if ("result" in message) console.log(message.result);
}

The Python example on the same page may also need updating if it has an equivalent required flag (e.g., allow_dangerously_skip_permissions=True).

Impact

High - Prevents users from using a feature

Additional Context

View original on GitHub ↗

This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗