@braintrust/pi-extension

What this package can reach

Detected automatically from the source at version 0.10.0. This describes access, not safety — you decide whether it's appropriate for what the package claims to do.

• 🤖
  Behavior — Changes how the agent thinks Modifies the system prompt, injects messages, or rewrites conversation context.
• ⚡
  Commands — Runs shell commands Spawns processes on your machine.
• 🔑
  Credentials — Handles your API keys Reads or passes provider credentials. Highest-trust capability there is.
• 📁
  Files — Reads files outside your project Touches paths beyond the working directory, such as your home folder.
• ⇄
  Intercepts tools — Can block or rewrite tool calls Subscribes to tool_call/tool_result/input. Can change a command after you approved the one displayed.
• 📡
  LLM traffic — Sees raw model API traffic Reads or replaces provider requests, headers or responses — including your prompts.
• ▤
  UI — Draws its own interface Renders widgets, footers, dialogs or full-screen views.