What is Anything2Ontology CLAUDE.md?

Project instructions for Anything2Ontology, a pipeline that turns files, web pages, and code repositories into structured knowledge for coding agents. They explain its design principles and module boundaries.

Use them when building or changing parsers, extractors, schemas, logging, or other parts of the knowledge-conversion pipeline.

They help agents load only the context they need and keep independent parts connected through clear data formats.

Anything2Ontology CLAUDE.md — Instructions file for Claude Code by kitchen-engineer42: Project instructions for Anything2Ontology, a pipelin

Install

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.

agentmods

npx agentmods add instructions/kitchen-engineer42/anything2ontology/claude-md

Clone the repo

git clone --depth 1 https://github.com/kitchen-engineer42/Anything2Ontology

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kitchen-engineer42/anything2ontology/claude-md.svg)](https://agentmods.dev/instructions/kitchen-engineer42/anything2ontology/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kitchen-engineer42/anything2ontology/claude-md"><img src="https://agentmods.dev/badge/instructions/kitchen-engineer42/anything2ontology/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,321 This file is loaded in full into every session.

When invoked 3,321 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.03321	$0.03321
Opus 5	$0.01661	$0.01661
Sonnet 5	$0.00664	$0.00664
Haiku 4.5	$0.00332	$0.00332

Measured 6d ago against content hash 8d340ae5ebc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Anything2Ontology CLAUDE.md 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 6d 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.

CLAUDE.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anything2Ontology - Project Context

Overview

Anything2Ontology is a knowledge management and modelling pipeline that converts various media formats into a comprehensive ontology for coding agents. The pipeline transforms inputs (files, URLs, repos) into structured knowledge that can be used by AI coding assistants to build applications.

Key Design Principles

1. Agile Schema Design

Schemas have two parts:

Fixed part: Standard fields that are always present
JIT (Just-In-Time) part: Flexible metadata that agents can define case-by-case

Example: ParseResult has fixed fields (source_path, status) and a JIT metadata dict.

2. Loose Coupling

Modules are independent and communicate through well-defined interfaces (schemas). Each module can be developed, tested, and modified independently.

3. Load Context As Needed

Like Claude Code's SKILL.md approach - read headers first to decide whether to load full content. Minimize context loading until necessary.

4. Atomic Tools

Human behavioral sequences expressed in natural language should be encapsulated into atomic, deterministic tools (parsers, extractors).

5. Dual-Format Logging

All operations generate both:

JSON logs (for machine parsing)
Plain text logs (for human reading)

Project Structure

Anything2Ontology/
├── src/
│   ├── anything2markdown/     # Module 1: Universal parser
│   │   ├── parsers/           # File parsers (MarkItDown, MinerU, PaddleOCR-VL, Tabular)
│   │   ├── url_parsers/       # URL parsers (YouTube, Bilibili, FireCrawl, Repomix)
│   │   ├── utils/             # Logging, file utils, retry logic
│   │   ├── schemas/           # ParseResult schema
│   │   ├── router.py          # Routing logic
│   │   ├── pipeline.py        # Main orchestration
│   │   └── cli.py             # CLI interface (anything2md)
│   ├── markdown2chunks/       # Module 2: Smart chunking
│   │   ├── chunkers/          # HeaderChunker, LLMChunker
│   │   ├── utils/             # Token estimation, Levenshtein
│   │   ├── schemas/           # Chunk, ChunksIndex
│   │   ├── router.py          # Markdown vs JSON routing
│   │   ├── pipeline.py        # Main orchestration
│   │   └── cli.py             # CLI interface (md2chunks)
│   ├── chunks2skus/           # Module 3: Knowledge extraction
│   │   ├── extractors/        # Factual, Relational, Procedural, Meta
│   │   ├── utils/             # Logging, LLM client
│   │   ├── schemas/           # SKU, LabelTree, Glossary, Index
│   │   ├── router.py          # Load chunks, route to extractors
│   │   ├── pipeline.py        # Main orchestration
│   │   └── cli.py             # CLI interface (chunks2skus)
│   └── skus2ontology/         # Module 4: Ontology assembly
│       ├── utils/             # Logging, LLM client (with multi-turn)
│       ├── schemas/           # OntologyManifest, ChatSession
│       ├── assembler.py       # Copy SKUs, rewrite paths
│       ├── chatbot.py         # Interactive spec.md generation
│       ├── readme_generator.py # Template-based README.md
│       ├── pipeline.py        # Main orchestration
│       └── cli.py             # CLI interface (skus2ontology)
├── input/                     # User input files
├── output/                    # Module 1 output (flat structure)
│   ├── chunks/                # Module 2 output (chunked markdown)
│   ├── passthrough/           # JSON files (unchanged)
│   └── skus/                  # Module 3 output (knowledge units)
├── ontology/                  # Module 4 output (self-contained ontology)
├── logs/                      # JSON and text logs
└── module_design/             # Design docs for each module

Read the full file on GitHub · 289 lines

Changes

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.

6d ago First seen · 289 lines · 3,321 tokens per session scan A 8d340ae5ebc2

Subscribe to this mod's changes

Anything2Ontology CLAUDE.md is an instructions file published in the GitHub repository kitchen-engineer42/Anything2Ontology (133 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 3,321 tokens to every session, about $0.0166 per session on Opus 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.

Data and AI

GPT-RAG release.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.

Azure/GPT-RAG · 207 tokens

Anything2Ontology CLAUDE.md