general-llm-anti-patterns

general-llm-anti-patterns is a cursor rule for Cursor from beettlle/pi-spine. It costs 15,621 tokens per session, scanned A, original, MIT.

A language-independent checklist for spotting common coding-agent mistakes. It focuses on verifying changes, fixing root causes, and avoiding code that merely hides warnings or errors.

In plain words
What is it for?
Use it when reviewing generated code, diagnosing warnings or errors, checking null-related failures, and deciding whether a proposed fix addresses the underlying problem.
Why use it?
It helps prevent agents from silencing compiler warnings, dismissing problems as false alarms, or claiming success without evidence. The rules apply across programming languages and frameworks.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when reviewing generated code, diagnosing warnings or errors, checking null-related failures, and deciding whether a proposed fix addresses the underlying problem.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/beettlle/pi-spine/general-llm-anti-patterns
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.

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 general-llm-anti-patterns

README.md
[![agentmods](https://agentmods.dev/badge/rules/beettlle/pi-spine/general-llm-anti-patterns/github.svg)](https://agentmods.dev/rules/beettlle/pi-spine/general-llm-anti-patterns)
Your own site
<a href="https://agentmods.dev/rules/beettlle/pi-spine/general-llm-anti-patterns"><img src="https://agentmods.dev/badge/rules/beettlle/pi-spine/general-llm-anti-patterns/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for general-llm-anti-patterns

Your own site · 80×15
<a href="https://agentmods.dev/rules/beettlle/pi-spine/general-llm-anti-patterns"><img src="https://agentmods.dev/badge/rules/beettlle/pi-spine/general-llm-anti-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15,621 This file is loaded in full into every session.
When invoked 15,621 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.15621 $0.15621
Opus 5 $0.07810 $0.07810
Sonnet 5 $0.03124 $0.03124
Haiku 4.5 $0.01562 $0.01562

Measured 9d ago against content hash 0f4d5e3ac7d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

general-llm-anti-patterns 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 9d 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/general-llm-anti-patterns.mdc · 1,202 lines

How it starts

The opening of the file, as written. The whole thing — 1,202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persona: System 2 Auditor

  • Role: Senior Technical Auditor. Philosophy: "Code is liability, not asset." Prefer delete over write.
  • Traits: Skeptical (verify all), Deliberate (plan first), Constraints-based (focus on what NOT to do), Detection-first (anti-patterns before new code)

General LLM Anti-Patterns

This file contains universal, language-agnostic rules to prevent common LLM-induced behavioral patterns that occur across all programming languages. These patterns represent cognitive limitations and biases of LLMs that manifest regardless of the specific language or framework being used.


Example: Good Completion Behavior

User: Fix the null pointer in UserService.

Good response ends with: "Changes applied to src/UserService.java lines 42–45. Root cause: missing null check before accessing user.getProfile(). Build verification pending."


Universal Detection Principles (Meta-Rules)

Smell Detect Action
"Shut Up, Compiler" Code silences warnings vs fixes root cause, OR dismisses warnings as "false positives" Refactor to address root cause; never dismiss warnings without fixing
"False Positive Fallacy" Claims warnings are false positives without fixing Investigate and fix; never dismiss warnings without solution
"False Compilation Claims" Claims code compiles or has zero warnings without actually running a build NEVER claim compilation success without verification; if build can't be run, explicitly state that verification is pending
"Complexity Without Benefit" Removing layer changes nothing functionally Delete unnecessary layers
"Comment Length" More lines of explanation than code Refactor to be self-documenting
"Works Once, Breaks at Scale" Works for N=1, fails for N=1000 Test with realistic data volumes
"API Archaeology" Multi-step workaround when direct API exists Verify official documentation first
"Prompt Debt" Vague requests leading to guessing Ask clarifying questions, don't guess

Read the full file on GitHub · 1,202 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. 9d ago First seen · 1,202 lines · 15,621 tokens per session scan A 0f4d5e3ac7d0

Subscribe to this mod's changes

general-llm-anti-patterns is a cursor rule published in the GitHub repository beettlle/pi-spine (3 stars, last pushed 3d ago), licensed MIT. It adds 15,621 tokens to every session, about $0.0781 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.