# LLMS-Explorer > Reference, reasoning and worked examples for llms.txt families — the spec, the rubric, conceptual vs proprietary files, vocabulary files — plus the concept tree, a directory of every known llms file with its conformance grade, and a recorded keyword/vector/hybrid run. Companion files: llms-full.txt (every page in full), llms-small.txt (the reference, essays and examples layers within ~50k tokens), llms-facts.txt (source-anchored units), llms-vocabulary.txt (the terms of this niche). ## Sections - [Overview](overview/llms.txt): 3 pages, ~177 tokens — Semantic indexing, recorded, The directory of known llms files, The concept tree - [Reference](reference/llms.txt): 14 pages, ~724 tokens — The attribute rubric, Changelog: spec v1 to v2, and the hub pipeline, The concept tree: nodes, frontier, and how to read a node page and 11 more - [Essays](essays/llms.txt): 4 pages, ~259 tokens — Conceptual vs proprietary llms files, Semantic indexing: two legs and a fusion, V2 vs V1 and 1 more - [Examples](examples/llms.txt): 13 pages, ~836 tokens — Which layer answers which question, Recipe 01 — Two hops with requests, Recipe 02 — Split root: follow a section index and 10 more - [Blog](blog/llms.txt): 8 pages, ~576 tokens — Abstracting one concept out of many docsets, Anchors that point nowhere, Turning a customer's docs into an llms family and 5 more