epistract CLAUDE.md

epistract CLAUDE.md is an instructions file for coding agents from usathyan/epistract. It costs 4,426 tokens per session, scanned A, original, MIT.

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.

In plain words
What is it for?
Use them when changing extraction pipelines, adding domains, handling PDFs or other supported files, working with large documents, or maintaining the Python project.
Why use it?
They keep contributions compatible with the framework's domain-pluggable design and document-processing constraints.

Instructions file

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/usathyan/epistract/claude-md
Clone the repo
git clone --depth 1 https://github.com/usathyan/epistract

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.

agentmods badge for epistract CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/usathyan/epistract/claude-md.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.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,426 This file is loaded in full into every session.
When invoked 4,426 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04426 $0.04426
Opus 5 $0.02213 $0.02213
Sonnet 5 $0.00885 $0.00885
Haiku 4.5 $0.00443 $0.00443

Measured 5d ago against content hash 436ffa5a698d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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 · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 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 · 273 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.

  1. 5d 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 20d ago), licensed MIT. It adds 4,426 tokens to every session, about $0.0221 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 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens