project-rules

Global development rules for the AgentForge project, covering code style, software structure, security, testing, and use of third-party libraries.

In plain words
What is it for?
Use them for any AgentForge development task, including implementation, refactoring, input validation, error handling, and automated tests.
Why use it?
They give coding agents a shared standard so changes remain focused, secure, testable, and consistent with the existing project.

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/mrzroot/agentforge/project-rules
Clone the repo
git clone --depth 1 https://github.com/mrzroot/agentforge

Made for: Cursor.

Per session 215 This file is loaded in full into every session.
When invoked 215 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 $0.00215 $0.00215
Opus 5 $0.00108 $0.00108
Sonnet 5 $0.00043 $0.00043
Haiku 4.5 $0.00021 $0.00021

Measured yesterday against content hash acebc1709edd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-rules 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 yesterday.

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.

.cursor/rules/project-rules.mdc · 26 lines

What it actually says

agentforge Development Guidelines

1. Core Principles

  • Write minimal, concise, and robust code. Avoid over-engineering (YAGNI).
  • Follow language idioms and leverage the standard library before third-party abstractions.
  • Never compromise on security, input validation, error handling, or accessibility.
  • Maintain existing style, patterns, and architectural conventions across edits.

2. Architecture & Patterns

  • Keep modules focused, decoupled, and single-responsibility.
  • Colocate tests, types, and documentation with the corresponding modules.

3. Security Requirements

  • Never hardcode API keys, secrets, credentials, or private tokens in source code or rules.
  • Sanitize and validate all external inputs, request payloads, and query parameters.

4. Testing Protocols

  • Ensure all new features, edge cases, and bug fixes have automated test coverage.
  • Keep tests deterministic, isolated, and fast.
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. yesterday First seen · 26 lines · 215 tokens per session scan A acebc1709edd

Subscribe to this mod's changes

project-rules is a cursor rule published in the GitHub repository mrzroot/agentforge (2 stars, last pushed 15d ago), licensed MIT. It adds 215 tokens to every session, about $0.0011 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.