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.
git clone --depth 1 https://github.com/langfuse/langfuse-docsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/langfuse/langfuse-docs/documentation-pages)<a href="https://agentmods.dev/rules/langfuse/langfuse-docs/documentation-pages"><img src="https://agentmods.dev/badge/rules/langfuse/langfuse-docs/documentation-pages/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/langfuse/langfuse-docs/documentation-pages"><img src="https://agentmods.dev/badge/rules/langfuse/langfuse-docs/documentation-pages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00738 | $0.00738 |
| Opus 5.5 | $0.00295 | $0.00295 |
| Sonnet 5.5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
documentation-pages scanned grade A with 0 findings 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 1mo ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Here's a continuation and elaboration of the guidelines for creating documentation pages for Langfuse, based on the existing documentation structure and content style observed across various files:
Langfuse Documentation Creation Guide
General Structure
Each documentation page typically follows a structured format to ensure consistency and ease of understanding. Here’s a breakdown of the common elements:
-
Metadata Block: At the top of each document, include YAML front matter that specifies metadata such as title, description, and category. This helps in SEO optimization and categorizing the content.
--- title: Title of the Document description: A brief description of what the document covers. category: Category Name --- -
Introduction: Start with a brief introduction that outlines what the document will cover and why it’s important. This section sets the context for the readers.
-
Prerequisites: If applicable, list any prerequisites that readers need to fulfill before they can effectively use the documentation. This could include software installations, account setups, or background knowledge.
-
Step-by-Step Instructions: Provide detailed, actionable steps for the users to follow. Use numbered lists for sequences that need to be followed in order.
-
Code Snippets: Include code examples where necessary. Use syntax highlighting to improve readability. Ensure that any placeholders are clearly indicated.
import langfuse # Replace 'your_api_key' with your actual API key langfuse.configure(api_key='your_api_key') -
Images and Diagrams: Use images and diagrams to explain concepts that are difficult to convey through text alone. Wrap images in a
<Frame>component to maintain styling consistency.<Frame className="my-10" fullWidth>  </Frame> -
Tips and Notes: Use callouts to highlight tips, warnings, or important notes. This can be done using markdown syntax or specific components if available.
> **Tip:** This is a helpful tip. -
FAQs and Troubleshooting: End the document with a FAQ or troubleshooting section to address common issues or questions related to the topic.
-
Further Resources: Provide links to related documents, external resources, or further reading to help users deepen their understanding.
Writing Style
- Clarity and Conciseness: Use clear and concise language. Avoid jargon unless it is commonly understood in the context of the documentation.
- Active Voice: Use active voice to make the content more engaging.
- Second Person: Address the reader directly using second person ("you") to make the text more user-friendly.
Formatting
- Headers: Use headers to organize content into logical sections. Headers should be hierarchical (
#,##,###). - Lists: Use bullet points for unordered lists and numbers for ordered lists.
- Links: Always use descriptive link texts instead of generic texts like "click here".
Accessibility
- Alt Texts for Images: Provide descriptive alt texts for all images to improve accessibility.
- Readable Fonts and Colors: Ensure that the text is readable by using sufficient contrast between text and background colors.
By adhering to these guidelines, the documentation will not only maintain a consistent style but also enhance the user experience, making it easier for readers to find, understand, and use the information they need.
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.
- 1mo ago First seen · 74 lines · 738 tokens per session scan A c8855d1a6cee
documentation-pages is a cursor rule published in the GitHub repository langfuse/langfuse-docs (246 stars, last pushed today), licensed MIT. It adds 738 tokens to every session, about $0.0030 per session on Opus 5.5. A static security scan graded it A with 0 findings. 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
js-sdk-genai-framework-instrumentation
Guide for implementing JS SDK agent and framework instrumentations, such as LangChain, LangGraph, OpenAI Agents, Claude Agent SDK, Google ADK, and Vercel AI.
coding-agents-hook
Authoring and testing coding-agent hook adapters, including payload probing, session state, capture modes, and plugin manifests. Consult the telemetry convention when changing canonical attributes.
coding-agents-convention
Canonical coding-agent telemetry schema, inbound mappings, and data contracts. Applies to semantic conventions, emission, processing, and readers—not hook implementation mechanics.
controller-design
Design principles and invariants for the OpenLIT controller (Go agent that discovers and instruments LLM workloads) and the Agents-page server layer that consumes its data.
frontend
UI, messaging, project hierarchy, and CE/enterprise-boundary guidance for OpenLIT client presentation code.
security-testing
Authorization, input validation, CE boundary, secrets, and test guidance for OpenLIT server code.