connect
Connect Logfire MCP and optionally record Claude Code sessions with native telemetry
Stop native Claude session telemetry while keeping Logfire MCP and skills available
> /plugin marketplace add pydantic/skillsHow it fires
How this command gets triggered: by you, by Claude, or both.
/disconnectContext preview
What this command does when you run it.
Stop native Claude session telemetry while keeping Logfire MCP and skills available
description: Stop native Claude session telemetry while keeping Logfire MCP and skills available
This command removes native Claude telemetry configuration, not the remote project, project token, account login, MCP connection, or application instrumentation. Explain that distinction and confirm the user's intent. If the user's request is ambiguous, ask whether they want to stop session capture, disconnect MCP, or both. If MCP-only, use Claude's native controls and skip the telemetry runtime entirely. Do not make users stop capture just to disconnect MCP, or clear their MCP login when they only asked to stop capture.
Run `python3 "${CLAUDE_PLUGIN_ROOT}/scripts/agent_runtime.py"` without `--install`. Using its returned executable and data directory:
1. Preview `--beta --no-input --output json agent claude --data-dir <data_dir> remove --dry-run`. 2. With confirmation, run the same operation with `--yes` instead of `--dry-run`. 3. Recheck `agent claude ... status`. Report the actual result and ask the user to restart Claude to stop exports from already-running sessions.
Do not delete the managed runtime or credential directory while the saved header helper may still reference them. The CLI refuses removal if managed fields were edited; surface that conflict rather than deleting fields by hand. If runtime or credentials are missing, do not claim capture has stopped or install software without asking. Help locate the original configuration.
Disabling/uninstalling the plugin is not a substitute for this operation. If the user also wants to disconnect MCP, use Claude's native `/mcp` controls to clear that connection separately. Do not revoke remote tokens unless asked.
Logfire, Pydantic AI, and Pydantic plugins for Claude Code, Codex, and Cursor. Instrument your code with Logfire, query and export the resulting telemetry, build LLM agents with Pydantic AI, and validate data with Pydantic.
Connect Logfire MCP and optionally record Claude Code sessions with native telemetry
Start a local Logfire dev session to send traces from your running app for debugging
Detect languages and frameworks in the current project and add Logfire instrumentation