What is epistract CLAUDE.md?

Project instructions for Epistract, a framework that turns document collections into knowledge graphs and analyzes what sources support, contradict, or omit. It includes rules for supported formats, domains, Python tooling, and large files.

Use them when changing extraction pipelines, adding domains, handling PDFs or other supported files, working with large documents, or maintaining the Python project.

They keep contributions compatible with the framework's domain-pluggable design and document-processing constraints.

How usathyan/epistract configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to usathyan/epistract. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/usathyan/epistract/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/usathyan/epistract

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/usathyan/epistract/claude-md/github.svg)](https://agentmods.dev/instructions/usathyan/epistract/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/usathyan/epistract/claude-md"><img src="https://agentmods.dev/badge/instructions/usathyan/epistract/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/usathyan/epistract/claude-md"><img src="https://agentmods.dev/badge/instructions/usathyan/epistract/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,244 This file is loaded in full into every session.

When invoked 4,244 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.04244	$0.04244
Opus 5.5	$0.01698	$0.01698
Sonnet 5.5	$0.00849	$0.00849
Haiku 4.5	$0.00424	$0.00424

Measured 1mo ago against content hash 3c848abaae79, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

epistract 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 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.

CLAUDE.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project

Epistract — Domain-Agnostic Knowledge Graph Framework

Epistract is a domain-agnostic knowledge graph framework. Plug in a domain schema (YAML + extraction prompts + epistemic rules), point at a document corpus, and get a structured knowledge graph with an epistemic analysis layer. It runs as a Claude Code plugin.

Core Value: Extract knowledge, not information. Any corpus, any domain — plug in a schema, get a knowledge graph with epistemic layer that reveals what documents say, what they contradict, and what they are missing.

Two pre-built domains demonstrate the framework:

drug-discovery — 17 entity types, 30 relation types for biomedical literature analysis
contracts — 11 entity types, 11 relation types for event/vendor contract analysis

Constraints

Tech stack: Python 3.11+, uv for package management
Document formats: PDF, DOCX, HTML, TXT, XLS, EML — 75+ formats via Kreuzberg with OCR fallback
Large files: Some documents are 12-31 MB — extraction must handle large documents
Domain pluggability: New domains added via configuration package (domain.yaml + SKILL.md + epistemic.py), no pipeline code changes
Existing codebase: Must preserve backward compatibility with all existing domains

Technology Stack

Languages

Python 3.11+ - Core runtime for knowledge graph building, molecular validation, plugin integration
Bash - Setup and utility scripts
YAML - Domain schema and configuration

Runtime

Python 3.11 or later (enforced in scripts/setup.sh)
Claude Code plugin runtime (runs as Claude Code marketplace plugin)
uv (preferred) - For installing Python dependencies
pip (fallback) - Alternative package management

Frameworks

sift-kg ≥0.9.0 - Knowledge graph construction, document ingestion, entity resolution, visualization, export
Kreuzberg ≥4.0 - Text extraction from 75+ document formats (PDF, DOCX, HTML, TXT, etc.) with OCR support for scans
pdfplumber ≥0.10 - Legacy PDF extraction backend
Pydantic ≥2.5 - Validation and serialization for DocumentExtraction models (entities, relations, attributes)
NetworkX ≥3.2 - Graph data structure (MultiDiGraph) for knowledge graph nodes and edges
pytest - Unit test framework (run: python -m pytest tests/test_unit.py -v)
ruff - Linting and code formatting (ruff check, ruff format)

Read the full file on GitHub · 251 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.

1mo ago Changed · -22 lines · -182 tokens per session 3c848abaae79
2mo ago First seen · 273 lines · 4,426 tokens per session scan A 436ffa5a698d

Subscribe to this mod's changes

epistract CLAUDE.md is an instructions file published in the GitHub repository usathyan/epistract (8 stars, last pushed 5d ago), licensed MIT. It adds 4,244 tokens to every session, about $0.0170 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 2026-08-31.

epistract CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
epistract CLAUDE.mdusathyan/epistract	Instructions file	8	5d ago	MIT	A	4,244	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

epistract: Instructions file for Claude Code