000-core

000-core is a cursor rule for Cursor from Haohao-end/openagent. It costs 193 tokens per session, scanned A, original, MIT.

A set of coding rules for building the LMForge language-model operations platform in Python. It defines formatting, typing, logging, dependency setup, secret handling, and response style.

In plain words
What is it for?
Use it when writing or changing LMForge Python code, especially when adding services, handling configuration, logging events, or preparing complete code changes.
Why use it?
It keeps the codebase consistent and easier to review. It also reduces common production problems such as exposed secrets, unclear errors, and unmanaged dependencies.

Cursor rule for Cursor

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 rules/haohao-end/openagent/000-core
Clone the repo
git clone --depth 1 https://github.com/Haohao-end/openagent

Made for: Cursor.

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 000-core

README.md
[![agentmods](https://agentmods.dev/badge/rules/haohao-end/openagent/000-core.svg)](https://agentmods.dev/rules/haohao-end/openagent/000-core)
Your own site
<a href="https://agentmods.dev/rules/haohao-end/openagent/000-core"><img src="https://agentmods.dev/badge/rules/haohao-end/openagent/000-core.svg" alt="Measured on agentmods" height="20"></a>
Per session 193 This file is loaded in full into every session.
When invoked 193 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 $0.00193 $0.00193
Opus 5 $0.00097 $0.00097
Sonnet 5 $0.00039 $0.00039
Haiku 4.5 $0.00019 $0.00019

Measured 3d ago against content hash 07fa2756e889, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

000-core 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 3d 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.

api/.cursor/rules/000-core.mdc · 20 lines

What it actually says

You are an elite full-stack Python engineer building a production-grade LLMOps platform called LMForge.

Core Principles (NEVER violate):

  • Strictly follow PEP 8, Black formatting, and Ruff linting.
  • Use comprehensive type hints everywhere (Python 3.11+ features preferred).
  • Prefer explicit, readable code: DRY, KISS, and "explicit is better than implicit".
  • Use structured logging (never print() in production code).
  • Use Injector for ALL dependency injection (never manual instantiation in production code).
  • Never hardcode secrets — always use environment variables via dotenv.

Response style:

  • Be concise, technical, and professional.
  • Output complete, runnable code blocks only.
  • Never explain unless explicitly asked.
  • When modifying code, output full file context or use @file references.
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. 3d ago First seen · 20 lines · 193 tokens per session scan A 07fa2756e889

Subscribe to this mod's changes

000-core is a cursor rule published in the GitHub repository Haohao-end/openagent (805 stars, last pushed 1mo ago), licensed MIT. It adds 193 tokens to every session, about $0.0010 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.