engineering-philosophy

engineering-philosophy is a cursor rule for Cursor from beettlle/pi-spine. It costs 0 tokens per session (2,929 once invoked), scanned A, original, MIT.

A set of engineering principles focused on safety, performance, developer experience, and keeping software simple.

In plain words
What is it for?
Evaluating or shaping engineering decisions, including when to delete code, revise an initial design, and reduce maintenance risks.
Why use it?
It gives agents guidance for avoiding unnecessary code, abstractions, and complexity during design and implementation.

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/beettlle/pi-spine/engineering-philosophy
Clone the repo
git clone --depth 1 https://github.com/beettlle/pi-spine

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 engineering-philosophy

README.md
[![agentmods](https://agentmods.dev/badge/rules/beettlle/pi-spine/engineering-philosophy.svg)](https://agentmods.dev/rules/beettlle/pi-spine/engineering-philosophy)
Your own site
<a href="https://agentmods.dev/rules/beettlle/pi-spine/engineering-philosophy"><img src="https://agentmods.dev/badge/rules/beettlle/pi-spine/engineering-philosophy.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,929 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.02929
Opus 5 $0.00000 $0.01465
Sonnet 5 $0.00000 $0.00586
Haiku 4.5 $0.00000 $0.00293

Measured 4d ago against content hash a687a7ddf83e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineering-philosophy 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 4d 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.

.cursor/rules/engineering-philosophy.mdc · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engineering Philosophy

Design goals: Priority is Safety, then Performance, then Developer Experience.

Core Beliefs

1.1 Simplicity is a Feature (CRIT)

CRITICAL: Every line of code is a liability. The best code is code you didn't write.

❌ Bad: class Service { func get() { return repo.get() } } (unnecessary layer) ✅ Good: Delete unnecessary layers, prefer deletion over addition ⚠️ Why: Complexity kills maintainability, increases bugs, slows development 🔧 Fix: Fight complexity; delete code that doesn't add value 📍 See: general-llm-anti-patterns.mdc section 1.1 (Ghost Layer Prevention)

Detect: Unnecessary abstractions, wrapper classes, code that adds no value


1.1a Simplicity is the Hardest Revision

CRITICAL: Real simplicity comes from iteration and "throw one away," not from the first attempt.

❌ Bad: Shipping first draft as "simple", no revision passes, assuming simple = quick ✅ Good: Multiple passes to simplify; revise until design is minimal and clear ⚠️ Why: First attempt is rarely simplest; iteration reveals the super idea that solves axes together 🔧 Fix: Budget revision time; simplify after it works 📍 See: engineering-philosophy.mdc section 1.3 (Make it Work, Make it Right, Make it Fast)

Detect: One-pass "simple" solutions, no design revision, complexity defended as "good enough"


1.1b Zero Showstopper Policy

CRITICAL: Don't ship known critical bugs or unbounded risks; fix showstoppers before merge.

❌ Bad: Merging with known unbounded loops, unbounded queues, or critical correctness bugs "to fix later" ✅ Good: Bounded loops/queues, fail-fast on limits, fix showstoppers in design or implementation before merge ⚠️ Why: The second time may not transpire; shipping known critical debt undermines progress 🔧 Fix: Enforce bounded iteration and fail-fast; resolve critical issues before merge 📍 See: general-llm-anti-patterns.mdc section 2.4 (Bounded loops and queues)

Detect: Unbounded loops or queues, known critical bugs deferred, merge with "we'll fix later" on showstoppers

Read the full file on GitHub · 271 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. 4d ago First seen · 271 lines · 0 tokens per session scan A a687a7ddf83e

Subscribe to this mod's changes

engineering-philosophy is a cursor rule published in the GitHub repository beettlle/pi-spine (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,929 tokens. 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.