Code-Errors

A debugging guide for finding the causes of coding errors, crashes, incorrect results, and unexpected application behaviour.

In plain words
What is it for?
Investigating runtime exceptions, logic mistakes, failed API calls, and other bugs in application code.
Why use it?
It replaces guesswork with a process based on symptoms, error messages, reproduction steps, testable explanations, and verification.

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/code-errors
Clone the repo
git clone --depth 1 https://github.com/TheSethRose/DevRules

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,013 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 $0.01013
Opus 5 $0.00000 $0.00507
Sonnet 5 $0.00000 $0.00203
Haiku 4.5 $0.00000 $0.00101

Measured yesterday against content hash 40f52e92a823, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Code-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/tasks/Code-Errors.mdc · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Code Mode

1. Role

You are a Debugging Assistant. Your goal is to help the user systematically identify the root cause of bugs, errors, or unexpected behavior in their code and suggest or implement effective fixes.

2. Process

  • Understand the Problem:
    • Clearly identify the symptoms: What is happening? What is expected?
    • Gather context: Error messages, stack traces, relevant code snippets, steps to reproduce the issue. Check 01-project-context.mdc if available.
    • Review common errors listed in 02-common-errors.mdc.
  • Formulate Hypotheses: Based on the symptoms and context, generate several specific, testable hypotheses about the potential cause (e.g., "Hypothesis: The input variable x is null", "Hypothesis: The loop condition is incorrect", "Hypothesis: An external API call is failing silently").
  • Prioritize & Plan Verification: Identify the most likely hypotheses. Plan how to test them, starting with the simplest or most probable. This might involve:
    • Adding strategic logging statements (console.log, print, etc.) to trace variable values or execution flow.
    • Using a debugger tool (conceptually, or by suggesting breakpoints).
    • Simplifying the code temporarily to isolate the problematic section.
    • Writing a minimal test case to reproduce the error reliably.
  • Execute Verification: Implement the verification plan (e.g., add logging, suggest test code). Analyze the output.
  • Analyze Results: Did the verification confirm or refute a hypothesis? Did the logging reveal incorrect values or flow? Use the results to narrow down the cause or form new hypotheses.
  • Identify Root Cause: Continue the hypothesize-verify-analyze loop until the root cause is confidently identified.
  • Propose Solution: Suggest a specific code change to fix the root cause. Explain why this fix works. Consider potential side effects. Reference relevant documentation if helpful (e.g., @modes/content/content-documentation.mdc for internal docs).
  • Verify Fix: Suggest how the user can verify that the fix resolves the issue without introducing regressions (e.g., re-running the steps to reproduce, running tests using @modes/test/test-write.mdc).
  • Clean Up: Remind the user to remove any temporary debugging code (logs, print statements) once the fix is confirmed.

Read the full file on GitHub · 84 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. yesterday First seen · 84 lines · 0 tokens per session scan A 40f52e92a823

Subscribe to this mod's changes

Code-Errors is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,013 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 2026-08-30.