02-common-errors

A project-specific template for recording common coding mistakes, unwanted patterns, and outdated syntax, with examples of the preferred approach. It starts empty and needs the user to add the project's rules.

In plain words
What is it for?
Use it to document recurring mistakes, correct examples, reasons for the rules, and links to project documentation or issue trackers.
Why use it?
It gives an AI assistant a reference for avoiding known problems in a particular codebase, rather than relying only on general programming advice.

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/thesethrose/devrules/02-common-errors
Clone the repo
git clone --depth 1 https://github.com/TheSethRose/DevRules

Made for: Cursor.

Per session 273 This file is loaded in full into every session.
When invoked 273 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 $0.00273 $0.00273
Opus 5 $0.00137 $0.00137
Sonnet 5 $0.00055 $0.00055
Haiku 4.5 $0.00027 $0.00027

Measured yesterday against content hash 01c960134a95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

02-common-errors 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/02-common-errors.mdc · 32 lines

What it actually says

Common Mistakes & Anti-Patterns for This Project

This file lists patterns the AI should actively avoid when working on this specific codebase.

Format Guide:

Use the following structure for each entry:

### MISTAKE: [Short Description of the Mistake]
- [PATTERN]: Describe when or how the mistake typically occurs.
- [BAD_EXAMPLE]: (Optional) Show a concise code snippet of the incorrect way.
- [GOOD_EXAMPLE]: Show a concise code snippet of the correct way.
- [SOLUTION/RULE]: Clearly state the rule or the correct approach to follow.
- [CONTEXT/REASON]: (Optional) Explain why the correct way is preferred (e.g., performance, maintainability, project standard).
- [REFERENCE]: (Optional) Link to relevant documentation, style guide section, or issue tracker.

Project-Specific Mistakes (User: Add your entries below)

MISTAKE:

  • [PATTERN]:
  • [BAD_EXAMPLE]:
  • [GOOD_EXAMPLE]:
  • [SOLUTION/RULE]:
  • [CONTEXT/REASON]:
  • [REFERENCE]:
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 · 32 lines · 273 tokens per session scan A 01c960134a95

Subscribe to this mod's changes

02-common-errors is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It adds 273 tokens to every session, about $0.0014 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 2026-08-30.