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.
npx agentmods add instructions/hmbown/hegelion/agents-mdgit clone --depth 1 https://github.com/Hmbown/HegelionWrote 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.
[](https://agentmods.dev/instructions/hmbown/hegelion/agents-md)<a href="https://agentmods.dev/instructions/hmbown/hegelion/agents-md"><img src="https://agentmods.dev/badge/instructions/hmbown/hegelion/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00636 | $0.00636 |
| Opus 5 | $0.00318 | $0.00318 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
Hegelion AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
hegelion/: core Python package (dialectic logic, MCP server, scripts, training utilities).tests/: pytest suite (files namedtest_*.py).docs/: specs and guides, includingdocs/HEGELION_SPEC.mdand MCP/agent docs.scripts/: release and maintenance scripts (e.g., PyPI publishing).hegelion-mcp-node/: Node/TypeScript MCP server for non-Python environments.hegelion-web/,apps/,extensions/,examples/,benchmarks/,hegelion-data/: auxiliary apps, docs, and datasets.
Build, Test, and Development Commands
- Python deps (recommended):
uv sync --dev - Python deps (pip):
pip install -e ".[dev]" - Run Python tests:
uv run pytest -v - Coverage:
uv run pytest --cov=hegelion --cov-report=html - Format/lint:
uv run black hegelion testsanduv run ruff check hegelion tests - Run MCP server:
python -m hegelion.mcp.server(orhegelion-serverwhen installed) - Node MCP server (from
hegelion-mcp-node/):npm install,npm run build,npm start
Coding Style & Naming Conventions
- Python formatted with Black (line length 100) and linted with Ruff.
- Prefer type hints on public functions and Google-style docstrings for public APIs.
- Tests live in
tests/and followtest_*.pynaming. - Branch names:
feature/...,fix/...,docs/...,refactor/....
Testing Guidelines
- Primary framework is
pytestwithpytest-asyncio. - New features should include tests that mirror package structure in
tests/. - If you touch
hegelion-mcp-node/, validate withnpm run build(no test script is defined).
Commit & Pull Request Guidelines
- Use Conventional Commit-style subjects seen in history, e.g.
feat: ...,fix(mcp): ...,docs: ...,chore: ...,style: ...,refactor: .... - PRs should include a clear summary, linked issues where relevant, and notes on tests run.
- Update
README.mdanddocs/HEGELION_SPEC.mdwhen behavior or APIs change; include screenshots forhegelion-web/UI 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 · 43 lines · 636 tokens per session scan A ab26ddef6578
Hegelion AGENTS.md is an instructions file published in the GitHub repository Hmbown/Hegelion (172 stars, last pushed 5mo ago), licensed MIT. It adds 636 tokens to every session, about $0.0032 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.
Other instructions, from other repositories
evalscope AGENTS.md
AGENTS.md instructions for modelscope/evalscope, covering agents.md, setup, build, lint, test, docs generation and quick eval.
langwatch CLAUDE.md
Claude Code instructions for langwatch/langwatch, covering langwatch, before you implement anything, development environment, running with no container runtime and local dev by hostname — thuishaven / portless (recommended).
Doberman-Core AGENTS.md
AGENTS.md instructions for DobermanCore/Doberman-Core, covering claude.md — doberman operating manual, 0. on startup (every session), 1. what this repository is, 2. architecture & extension points and 3. prime directives (non-negotiable).
benchmark-radar AGENTS.md
AGENTS.md instructions for ktwu01/benchmark-radar, covering repository instructions, glob rule: showcase and ui communication, example: simplify badge copy and keep its style, glob rule: benchmark radar audience and pull request merges.
Eval CLAUDE.md
Instructions for ai-twinkle/Eval, covering twinkle eval — 專案規範手冊（claude.md）, 目錄, 1. 專案定位與設計理念, 1.1 誕生背景 and 1.2 核心設計哲學.
AutoRAG AGENTS.md
AGENTS.md instructions for Marker-Inc-Korea/AutoRAG, covering autorag — pi-powered librarian agent, git workflow (binding), before any pr review, pr work, or new feature, after the work is finished and developer commands.