critical-rules-quick-reference

critical-rules-quick-reference is a cursor rule for Cursor from beettlle/pi-spine. It costs 2,416 tokens per session, scanned A, original, MIT.

A short reference of rules for producing careful coding-agent answers and changes. It covers evidence for build and test claims, concise output, and clear communication.

In plain words
What is it for?
Use it as a quick check before reporting results, describing changed files, claiming verification, or presenting a completion summary.
Why use it?
It reduces unsupported statements such as claiming that code builds or tests pass without showing verification. It also helps keep responses focused and code changes limited to the requested scope.

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/critical-rules-quick-reference
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 critical-rules-quick-reference

README.md
[![agentmods](https://agentmods.dev/badge/rules/beettlle/pi-spine/critical-rules-quick-reference.svg)](https://agentmods.dev/rules/beettlle/pi-spine/critical-rules-quick-reference)
Your own site
<a href="https://agentmods.dev/rules/beettlle/pi-spine/critical-rules-quick-reference"><img src="https://agentmods.dev/badge/rules/beettlle/pi-spine/critical-rules-quick-reference.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,416 This file is loaded in full into every session.
When invoked 2,416 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 $0.02416 $0.02416
Opus 5 $0.01208 $0.01208
Sonnet 5 $0.00483 $0.00483
Haiku 4.5 $0.00242 $0.00242

Measured 3d ago against content hash 94a7e95a20e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

critical-rules-quick-reference 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.

.cursor/rules/critical-rules-quick-reference.mdc · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Critical Rules Quick Reference

🚫 FORBIDDEN PHRASES (without proof)

"compiles", "builds", "zero warnings", "build succeeded" → Must show build output or say "verification pending"

Output Format

  • Code changes: only modified functions/lines, not entire files
  • File paths: backticks, e.g. src/Service.java
  • Build/test claims: show output or say "verification pending"
  • Completion: brief summary of what changed and why

Cooperative Communication (Grice-inspired)

Quick check before sending: Quality (evidence or "verification pending" + command attempted) · Quantity (match task depth) · Relation (answer the ask first) · Manner (outcome first, orderly, no filler).

Maxim Rule
Epistemic quality No unsupported build/test/API claims
Quantity Enough to decide/act; no essay for simple asks; no one-liner when design/audit requested
Relation On-scope; no unsolicited docs/refactors (see documentation-policy)
Manner Lead with answer; then steps/evidence; proportional length
Clear prose Active voice; short full sentences; one claim per sentence; cut pleasantries/filler; keep code/paths/APIs/errors exact

Details: general-llm-anti-patterns.mdc §9.6–9.8a

Top 15 Universal Anti-Patterns

1. Ghost Layer Prevention

❌ Bad: class Service { func get() { return repo.get() } } (>80% delegation) ✅ Good: Service coordinates multiple repos OR adds logic OR delete layer ⚠️ Why: Adds complexity without value, violates SRP 📍 Details: general-llm-anti-patterns.mdc section 1.1

2. Fake Abstraction Patterns

❌ Bad: actor Repo { func process() async { await MainActor.run { } } } (defeats isolation) ✅ Good: actor Repo { func process() async { /* actual async work */ } } ⚠️ Why: Creates illusion of concurrency without benefits, adds overhead 📍 Details: general-llm-anti-patterns.mdc section 1.2

3. Placeholder & Dead Code Ban

❌ Bad: func method() { throw NotImplementedError() } or _ = expensiveOperation() ✅ Good: Implement, remove, or mark unavailable with explanation ⚠️ Why: Broken functionality, wasted resources, technical debt 📍 Details: general-llm-anti-patterns.mdc section 1.3

Read the full file on GitHub · 203 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. 3d ago First seen · 203 lines · 2,416 tokens per session scan A 94a7e95a20e5

Subscribe to this mod's changes

critical-rules-quick-reference is a cursor rule published in the GitHub repository beettlle/pi-spine (3 stars, last pushed today), licensed MIT. It adds 2,416 tokens to every session, about $0.0121 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.