llms.txt Analyzer & Previewer
Analyze the structure and content of an llms.txt file. Preview the rendered Markdown, inspect sections and links, and calculate words, characters, file size and estimated tokens.
llms.txt Analyzer
Preview structure, sections, links and file metrics
Select Input Method
Project Title
Context Estimate
Estimated token usageTokens are estimated using a generic ~4 chars/token heuristic. Actual counts depend on the specific LLM tokenizer.
Observations
Rendered Markdown Preview
Structural Outline
Section Distribution
| Section Name | Links | Described | Internal | External | Tokens |
|---|
Resource Links
| Title | URL | Section | Type |
|---|
Detailed File Statistics
Content and link metrics from the analyzed file.
Basic Metrics
File content footprint.
Link Metrics
Resource and domain coverage.
What Is the llms.txt Analyzer & Previewer?
The llms.txt Analyzer & Previewer is a read-only diagnostic dashboard for inspecting the internal contents, structure, and token budget of an llms.txt file. Rather than validating compliance rules or testing server headers, the Analyzer helps you understand your file's composition: how many links each section holds, how descriptions are distributed, and how much context weight secondary resources add.
How the Analyzer Differs from Other Tools
Each tool in the LLMs.txt Lab suite addresses a distinct step in file management:
Analyzer (This Tool)
Inspects internal structure, measures words, characters, and estimated tokens, and previews rendered Markdown.
Validator →
Evaluates specification compliance (single H1, section rules) and live endpoint deployment health (HTTP status, headers).
Link Checker →
Performs live HTTP requests against all external destination URLs referenced inside the file to detect dead links.
Formatter →
Beautifies and normalizes whitespace, standardizes bullet styles, and sorts sections cleanly.
Six Analysis Views in the Dashboard
The dashboard parses your Markdown locally in the browser and presents six focused views:
- Overview: High-level project title, summary, total section count, total link count, and estimated token footprint.
- Preview: Sanitized, styled HTML rendering of the Markdown document so you can review how readers and assistants interpret your hierarchy.
- Structure: Interactive structural outline showing heading levels and link counts, exportable as JSON.
- Sections: Table breaking down each section by link count, percentage of links with descriptions, internal vs. external links, and per-section estimated tokens.
- Links: Searchable, filterable inventory of every link with section categorization, link type, and CSV export.
- Statistics: Deep numerical metrics covering character counts (with and without spaces), total words, physical and blank lines, unique URLs, and duplicate occurrences.
Core Context vs. Optional Token Estimates
Under the current specification, the ## Optional section holds secondary references (such as terms, privacy policies, or supplementary guides). The Analyzer calculates separate token estimates for Core Context (excluding optional sections) and Full Document Context. This lets developers budget their prompt tokens accurately when feeding documentation directly into language model context windows.
Publish your llms.txt automatically
Generate and maintain a clean /llms.txt endpoint from your WordPress posts, pages, categories and public custom post types.