langfuse

Claude Observability Plugin — Development skill for Claude Code

Development community

The Langfuse Observability Plugin for the Claude Code Marketplace.

How to install Claude Observability Plugin

This entry records only its repository, not the path inside it, so there is no exact command to give. Open langfuse/claude-observability-plugin and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude Observability Plugin does

The Langfuse Observability Plugin for the Claude Code Marketplace.

Alternatives in Development

Every Marketplace — pattern 11.2k ★
Agent Skills Platform — Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery 2.4k ★
Agent Skill Creator — Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery 2.3k ★

README

Langfuse Observability Plugin for Claude Code

This plugin sends [Claude Code](https://claude.com/claude-code) sessions to [Langfuse](https://langfuse.com). It records the user prompts, the agent turns, the model generations with their tokens and cost, and the tool calls, with no change to your code.

Langfuse also documents this integration on the [Claude Code integration page](https://langfuse.com/integrations/developer-tools/claude-code).

What can this integration trace?

The plugin runs as a Claude Code hook and reads the session transcript on every turn, so tracing needs no change to the way you work:

Agent turns: one trace per user prompt, with all turns of a session grouped under one session ID.
Model generations: every assistant message with inputs, outputs, cost and token usage, including cache reads and a cache write split by the lifetime it was written under, which each carry their own rate. token usage, including cache-read and reasoning splits.
Thinking: assistant thinking blocks attach to the generation that produced them and render as thinking blocks in the trace. Claude Code writes the thinking text only when showThinkingSummaries is true in its settings.
Tool calls: each tool Claude Code invokes, with input and output.
Subagents: subagent and Workflow-spawned agent transcripts nest under the turn that started them.
Skills: traces carry a skill: tag for every skill a turn invokes.
Images: pasted images and screenshots from tool results upload as Langfuse media and render inside the trace.

Tracing covers the `claude` CLI and desktop **Code** mode; regular Claude Desktop **Chat** mode runs no Claude Code hooks and is not traced.

Prerequisites

One of:

uv (recommended) on PATH. The hook uses uv run --script and installs the Langfuse SDK from the script metadata.
Python 3.10+ as python3 with langfuse>=4.7,<5 installed. This is o