What is Hegelion CLAUDE.md?

Development instructions for Hegelion, a system that creates structured reasoning prompts and can run coding workflows through connected backends. It covers dialectical reasoning—comparing a thesis with an opposing view—and a player-coach coding process.

Developing Hegelion, running its test suite or individual tests, checking coverage, formatting and linting code, and starting its server.

It gives coding agents the project background and the commands needed to install dependencies, test, format, lint, and run the system.

How Hmbown/Hegelion configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Hmbown/Hegelion. 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/Hmbown/Hegelion/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Hmbown/Hegelion

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/hmbown/hegelion/claude-md/github.svg)](https://agentmods.dev/instructions/hmbown/hegelion/claude-md)

Your own site

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

Per session 1,168 This file is loaded in full into every session.

When invoked 1,168 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	$0.01168	$0.01168
Opus 5.5	$0.00467	$0.00467
Sonnet 5.5	$0.00234	$0.00234
Haiku 4.5	$0.00117	$0.00117

Measured 2mo ago against content hash 30db8e8693e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Hegelion 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 2mo 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 · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What is Hegelion

Prompt-driven dialectical reasoning and autocoding system for LLMs. It generates structured prompts by default and can optionally execute them through MCP backends. Two modes:

Dialectical Reasoning — Thesis → Antithesis → Synthesis (optional Council of perspectives and Judge)
Autocoding (Player-Coach) — Based on Block AI's g3 agent research. Player implements, Coach independently verifies against requirements. Requirements are the single source of truth; the Coach discards the Player's self-report.

Build & Development Commands

# Install dependencies (uv recommended)
uv sync --dev

# Run all tests
uv run pytest -v

# Run a single test file
uv run pytest tests/test_autocoding.py -v

# Run a single test
uv run pytest tests/test_autocoding.py::test_function_name -v

# Coverage
uv run pytest --cov=hegelion --cov-report=html

# Format
uv run black hegelion tests

# Lint
uv run ruff check hegelion tests

# Run MCP server
hegelion-server              # installed entry point
python -m hegelion.mcp.server  # from source

# Self-test MCP server tools
hegelion-server --self-test

Code Style

Black formatter, line length 100. Black excludes hegelion/engine.py and .gemini/.
Ruff linter. Both enforced in CI.
Type hints on public functions, Google-style docstrings for public APIs.
Pytest with asyncio_mode = "auto" — async test functions just work.
Conventional commits: feat:, fix(mcp):, docs:, refactor:, style:, chore:.

Architecture

Core Design Principle — Prompt-Driven First, Optional Backend Execution

The default MCP behavior is still prompt generation for the client (Claude Desktop, Cursor, etc.) to execute. Server-side execution is optional and now flows through a small backend layer (prompt, cli, codex_mcp, auto) so dialectic single-shot calls and coach turns can be executed without changing the core prompt/state model.

Read the full file on GitHub · 101 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.

2mo ago First seen · 101 lines · 1,168 tokens per session scan A 30db8e8693e2

Subscribe to this mod's changes

Hegelion CLAUDE.md is an instructions file published in the GitHub repository Hmbown/Hegelion (176 stars, last pushed 7mo ago), licensed MIT. It adds 1,168 tokens to every session, about $0.0047 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 2026-08-30.

AI Safety Evaluation LLM anthropic benchmarking mcp

Hegelion CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Hegelion CLAUDE.mdHmbown/Hegelion	Instructions file	176	7mo ago	MIT	A	1,168	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	today	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

Hegelion: Instructions file for Claude Code