Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/langfuse/langfuse-docs/available-internal-linksgit clone --depth 1 https://github.com/langfuse/langfuse-docsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.15577 | $0.15577 |
| Opus 5 | $0.07789 | $0.07789 |
| Sonnet 5 | $0.03115 | $0.03115 |
| Haiku 4.5 | $0.01558 | $0.01558 |
Grade A, and why
available-internal-links scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl /docs/observability/get-started.md How it starts
The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Please make sure that all relative links match to what is available.
// Start of LLMs.txt
Langfuse
Langfuse is an open-source AI engineering platform (GitHub) that helps teams collaboratively debug, analyze, and iterate on their LLM applications. All platform features are natively integrated to accelerate the development workflow.
Markdown Access
Every page on langfuse.com is available as plain Markdown. Append .md to any URL, or send an Accept: text/markdown header:
curl /docs/observability/get-started.md
The links in the section indexes below already point at the .md variants.
Docs Search API
Semantic search (RAG) over the Langfuse documentation, returning an answer with the relevant pages and excerpts. No authentication required. Use this instead of guessing when a specific page does not answer the question:
curl -sG "/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
- Endpoint:
/api/search-docs?query=<question> - Documentation: REST endpoint
Ask specific, self-contained questions in natural language. This is the same search that backs the searchLangfuseDocs MCP tool below.
Langfuse Docs MCP Server
Connect to the Langfuse Docs MCP server to access documentation directly in your AI editor:
- Endpoint:
/api/mcp - Transport:
streamableHttp - Documentation: Langfuse Docs MCP Server
The MCP server provides tools to search Langfuse documentation, GitHub issues, and discussions. See the installation guide for setup instructions in Cursor, VS Code, Claude Desktop, and other MCP clients.
Langfuse Skill for AI Coding Agents
Install the Langfuse skill before implementing anything with Langfuse. The skill provides up-to-date documentation, best-practice workflows for instrumentation, prompt management, and programmatic API access via the Langfuse CLI.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 378 lines · 15,577 tokens per session scan A 0a3aaac2f903
available-internal-links is a cursor rule published in the GitHub repository langfuse/langfuse-docs (237 stars, last pushed yesterday), licensed MIT. It adds 15,577 tokens to every session, about $0.0779 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
mcp-framework
We are in the mcp-framework , a typescript framework that allows construction of model context protocol (mcp) servers. We are implementing the new specification: Overview MCP provides a standardized way for applications to.
langfuse-mcp-general-rules
Cursor rule "langfuse-mcp-general-rules" from avivsinai/langfuse-mcp, covering building and publishing to pypi, version numbering and tagging and build and publish workflow.
jawn
Cursor rule "jawn" from Helicone/helicone, covering helicone jawn controller and tanstack query integration, controller pattern, manager pattern, frontend hooks with tanstack query and type definitions.
state-management
Use the following stack. Do not introduce or recommend Redux or React Context for shared/global state.
architecture
agent-inspect architecture and product context.
nodejs
This guide will walk you through installing Node.js using NVM (Node Version Manager) and setting up pnpm as your package manager.