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.
git clone --depth 1 https://github.com/beettlle/pi-spineWrote 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.
[](https://agentmods.dev/rules/beettlle/pi-spine/general-llm-anti-patterns)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 |
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.
- 9d ago First seen · 1,202 lines · 15,621 tokens per session scan A 0f4d5e3ac7d0
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.
Other cursor rules, from other repositories
error-handling-and-validation
A code-quality guide for handling errors, invalid inputs, edge cases, preconditions, logging, and user-friendly error messages.
css-render-blocking-diagnosis
Cursor rule "css-render-blocking-diagnosis" from adobecom/da-express-milo, covering css render-blocking diagnosis & resolution, critical learning from 98 pagespeed achievement, primary diagnostic protocol, step 1: css blocking symptom recognition and step 2: css loading sequence audit.
workflow-level1
Streamlined workflow for Level 1 Quick Bug Fix tasks.
modus-checkbox-value-inversion-react-short
Critical bug fix for ModusWcCheckbox value property inversion.
javascript-expert-performance
Profile first. Measure before and after. Never optimize without data.
5-bug-finder
APPLY WHEN investigating a bug.