From posthog
Adds PostHog LLM analytics to trace AI model usage with token counts, latency, and costs. Handles initial PostHog SDK setup and supports many providers and frameworks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/posthog:instrument-llm-analyticsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill to add PostHog LLM analytics that trace AI model usage in new or changed code. Use it after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and costs. If PostHog is not yet installed, this skill also covers initial SDK setup. Supports any provider or framework.
references/README.mdreferences/anthropic.mdreferences/autogen.mdreferences/azure-openai.mdreferences/basics.mdreferences/calculating-costs.mdreferences/cerebras.mdreferences/cohere.mdreferences/crewai.mdreferences/deepseek.mdreferences/dspy.mdreferences/fireworks-ai.mdreferences/google.mdreferences/groq.mdreferences/helicone.mdreferences/hugging-face.mdreferences/instructor.mdreferences/langchain.mdreferences/langgraph.mdreferences/litellm.mdUse this skill to add PostHog LLM analytics that trace AI model usage in new or changed code. Use it after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and costs. If PostHog is not yet installed, this skill also covers initial SDK setup. Supports any provider or framework.
Supported providers: OpenAI, Azure OpenAI, Anthropic, Google, Cohere, Mistral, Perplexity, DeepSeek, Groq, Together AI, Fireworks AI, xAI, Cerebras, Hugging Face, Ollama, OpenRouter.
Supported frameworks: LangChain, LlamaIndex, CrewAI, AutoGen, DSPy, LangGraph, Pydantic AI, Vercel AI, LiteLLM, Instructor, Semantic Kernel, Mirascope, Mastra, SmolAgents, OpenAI Agents.
Proxy/gateway: Portkey, Helicone.
Follow these steps IN ORDER:
STEP 1: Analyze the codebase and detect the LLM stack.
STEP 2: Research instrumentation. (Skip if PostHog LLM tracing is already set up.) 2.1. Find the reference file below that matches the detected provider or framework — it is the source of truth for callback setup, middleware configuration, and event capture. Read it now. 2.2. If no reference matches, use manual-capture.md as a fallback — it covers the generic event capture approach that works with any provider.
STEP 3: Install the PostHog SDK. (Skip if PostHog is already set up.)
STEP 4: Add LLM tracing.
STEP 5: Link to users.
STEP 6: Set up environment variables.
.env, .env.local, or framework-specific env files). If valid values already exist, skip this step.projects-get tool to retrieve the project's api_token. If multiple projects are returned, ask the user which project to use. If the MCP server is not connected or not authenticated, ask the user for their PostHog project API key instead.https://us.i.posthog.com for US Cloud or https://eu.i.posthog.com for EU Cloud.references/openai.md - Openai observability installation - docsreferences/azure-openai.md - Azure openai observability installation - docsreferences/README.md - PostHog.ai for .netreferences/anthropic.md - Anthropic ai observability installation - docsreferences/google.md - Google ai observability installation - docsreferences/cohere.md - Cohere ai observability installation - docsreferences/mistral.md - Mistral ai observability installation - docsreferences/perplexity.md - Perplexity ai observability installation - docsreferences/deepseek.md - Deepseek ai observability installation - docsreferences/groq.md - Groq ai observability installation - docsreferences/together-ai.md - Together ai observability installation - docsreferences/fireworks-ai.md - Fireworks ai observability installation - docsreferences/xai.md - Xai observability installation - docsreferences/cerebras.md - Cerebras ai observability installation - docsreferences/hugging-face.md - Hugging face ai observability installation - docsreferences/ollama.md - Ollama ai observability installation - docsreferences/openrouter.md - Openrouter ai observability installation - docsreferences/langchain.md - Langchain ai observability installation - docsreferences/llamaindex.md - Llamaindex ai observability installation - docsreferences/crewai.md - Crewai observability installation - docsreferences/autogen.md - Autogen ai observability installation - docsreferences/dspy.md - Dspy ai observability installation - docsreferences/langgraph.md - Langgraph ai observability installation - docsreferences/pydantic-ai.md - Pydantic ai observability installation - docsreferences/vercel-ai.md - Vercel ai SDK observability installation - docsreferences/litellm.md - Litellm ai observability installation - docsreferences/instructor.md - Instructor ai observability installation - docsreferences/semantic-kernel.md - Semantic kernel ai observability installation - docsreferences/mirascope.md - Mirascope ai observability installation - docsreferences/mastra.md - Mastra ai observability installation - docsreferences/smolagents.md - Smolagents ai observability installation - docsreferences/openai-agents.md - Openai agents SDK observability installation - docsreferences/portkey.md - Portkey ai observability installation - docsreferences/helicone.md - Helicone ai observability installation - docsreferences/manual-capture.md - Manual capture ai observability installation - docsreferences/basics.md - Ai observability basics - docsreferences/traces.md - Traces - docsreferences/calculating-costs.md - Calculating llm costs - docsEach provider reference contains installation instructions, SDK setup, and code examples specific to that provider or framework. Find the reference that matches the user's stack.
If the user's provider isn't listed, use manual-capture.md as a fallback — it covers the generic event capture approach that works with any provider.
npx claudepluginhub anthropics/claude-plugins-official --plugin posthogInstruments codebases with LaunchDarkly AI metrics tracking, selecting the lowest-ceremony tier (managed runner, provider package, custom extractor, or manual) that captures duration, tokens, and success/error.