trustabl

Runs Trustabl — a static analyzer for agent reliability — against the current repository or a specified path. Analyzes code built with Claude Agent SDK, OpenAI Agents SDK, Google ADK, MCP, LangChain/LangGraph, CrewAI, AutoGen, Pydantic AI, or the Vercel AI SDK. Models the tools, agents, subagents, and skills declared in the repo, checks them against the Trustabl reliability and safety rule catalog, and produces enriched findings with AI explanations and concrete code fixes. Interactively shows each proposed fix as a diff and applies only the ones the user approves.

Enriches source files flagged by a Trustabl scan — adds what is missing and corrects what is wrong, guided entirely by the scan's own explanation and fix text. Use after `trustabl scan` to apply findings directly to source files without manual editing.

Use right after you write or modify AI agent, tool, subagent, or MCP-server code (OpenAI Agents SDK, Claude Agent SDK, Google ADK, MCP) to self-audit it for security and reliability misconfigurations with Trustabl before committing. Triggers on adding or editing an agent definition, a tool / @function_tool / @tool / tool() handler, a subagent markdown file, an MCP server registration, agent guardrails, or .claude/settings.json permissions. Runs Trustabl's `scan` tool via the plugin's bundled MCP server and guides remediation of the findings.

1 hook across 1 event