
Langfuse Observability Plugin
PluginLangfuse 官方插件:通过钩子把 Claude Code 会话中的提示词、模型调用、token 用量与成本、工具调用和子代理上报为 Langfuse trace,便于监控与复盘。需要 Langfuse 密钥(支持自托管),以及 uv 或 Python 3.10+。
Langfuse Observability Plugin for Claude Code
Claude Code plugin that sends Claude Code session telemetry to Langfuse. It traces user prompts, agent turns, model generations with their token usage and cost, thinking blocks, tool calls, skills, subagents, and pasted or returned images.
Langfuse also documents this integration on the Claude Code integration page.
Quick Start
Add the marketplace and install the plugin:
claude plugin marketplace add langfuse/Claude-Observability-Plugin
claude plugin install langfuse-observability@langfuse-observability
Restart Claude Code after installing, so that it loads the hook.
Tracing covers the claude CLI and the desktop app in Code mode. Claude
Desktop Chat mode runs no Claude Code hooks and is not traced.
Prerequisites
The plugin needs uv on PATH. The hook runs as a
uv script and installs the Langfuse SDK from its own inline script metadata.
Machines without uv fall back to Python 3.10+ as python3 with
langfuse>=4.7,<5 installed.
Without a usable runtime the hook writes the reason to its log and exits. It never blocks or slows Claude Code.
Langfuse Credentials
Configure the plugin from inside a Claude Code session. This is a Claude Code slash command, not a shell command:
/plugin configure langfuse-observability@langfuse-observability
You can also pass the values during install:
claude plugin install langfuse-observability@langfuse-observability \
--config LANGFUSE_PUBLIC_KEY=pk-lf-... \
--config LANGFUSE_SECRET_KEY=sk-lf-... \
--config LANGFUSE_BASE_URL=https://cloud.langfuse.com
Only LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY are required. Without
LANGFUSE_BASE_URL the plugin uses https://cloud.langfuse.com (EU region).
Get the keys from the API Keys page in your Langfuse project settings. The
secret key is held in your OS keychain, not in a file.
/plugin configure also lists the optional settings, such as the user ID,
debug logging, and image capture, with their defaults.
Updating
Automatic updates are off for marketplaces outside Anthropic's, so you run the update yourself.
claude plugin marketplace update langfuse-observability
claude plugin update langfuse-observability@langfuse-observability
Restart Claude Code afterwards. claude plugin list shows the installed
version.
Troubleshooting
The hook explains nearly every failure in
~/.claude/state/langfuse_hook.log. Send one message, then read the newest
lines. Turn on CC_LANGFUSE_DEBUG for verbose logging.
A log with no new lines means that the hook never started. Either the plugin is
disabled, or no usable runtime was found. Run claude plugin list from the
directory you work in, and put uv on the PATH of the app that starts Claude
Code.
Contributing
See the contributing guide.
License
相關資源

MLflow Skills
PluginMLflow 官方技能插件:让编码 agent 给 LLM 应用接入 MLflow Tracing、分析失败的 trace、搭建评测数据集与打分器、查询 token 与延迟指标,完成埋点、评测、迭代的闭环。需要 MLflow 3.8+。
mlflow/skills81
RTK (Rust Token Killer)
CLI在命令输出进入 agent 上下文之前做过滤和压缩的 Rust 命令行代理,覆盖 git、测试、grep、ls 等上百种命令,最多可减少约 90% 的 bash 输出;通过钩子自动改写 Claude Code、Codex 等 agent 执行的命令。
rtk-ai/rtk83.9k
Plugin Dev
Plugin开发 Claude Code 插件的工具包:7 个技能覆盖插件结构、钩子、MCP 集成、命令、子代理与技能编写,附八阶段引导式创建命令,以及代理生成、插件校验、技能评审三个子代理。Anthropic 官方维护。
anthropics/claude-code152k
Agent SDK Dev
Plugin用 /new-sdk-app 交互式搭建 Claude Agent SDK 项目(Python 或 TypeScript),再由校验代理按官方最佳实践检查依赖、配置与代码。Anthropic 官方维护。
anthropics/claude-code152k
Hookify
Plugin用一句话描述或分析近期对话自动生成钩子规则,以 Markdown 文件配置匹配条件,拦截或警告危险命令与不想要的写法,无需重启即生效。Anthropic 官方插件。
anthropics/claude-code152k
Claude Code Setup
Plugin扫描代码库,按类别推荐最合适的钩子、技能、MCP 服务器、子代理与斜杠命令;只分析不改文件,适合给项目快速配好 Claude Code。Anthropic 官方插件。
anthropics/claude-plugins-official42.9k