debugging

A debugging procedure that starts by exploring relevant files, collecting errors and other evidence, then testing several possible root causes. It also lists optional tools for browser, database, and library investigations.

In plain words
What is it for?
Use it to investigate application errors, frontend problems, database issues, library or API problems, and performance concerns.
Why use it?
It reduces guesswork by requiring context and evidence before changing code.

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/rm2thaddeus/pixel_detective/debugging
Clone the repo
git clone --depth 1 https://github.com/rm2thaddeus/Pixel_Detective

Made for: Cursor.

Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 860 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 $0.00003 $0.00860
Opus 5 $0.00002 $0.00430
Sonnet 5 $0.00001 $0.00172
Haiku 4.5 $0.00000 $0.00086

Measured yesterday against content hash ab76e4d73921, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debugging 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/debugging.mdc · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before starting to debug, take your time to explore the files related with the user request.

Once found, use appropriate MCP servers to gather relevant context and debug information:

MCP-Enhanced Debugging Workflow

1. Collect Context & Evidence

  • Error Analysis: Capture error messages, logs, stack traces
  • File Discovery: Use grep_search for exact matches, codebase_search for broader context
  • Frontend Issues:
    • Use Browser Tools MCP to capture console logs (mcp_browser-tools_getConsoleLogs, mcp_browser-tools_getConsoleErrors)
    • Capture network errors (mcp_browser-tools_getNetworkErrors)
    • Take screenshots (mcp_browser-tools_takeScreenshot) for visual issues
  • Database Issues: Use Supabase MCP to query data and check schema integrity
  • Library/API Issues: Use Context7 MCP to gather relevant documentation

2. Investigate Root Causes

  • List ≥3 hypotheses based on collected evidence
  • Confirm via targeted file reading (cat -n) & project structure (tree)
  • Frontend Root Causes: Run comprehensive audits (mcp_browser-tools_runAuditMode)
  • Performance Issues: Use mcp_browser-tools_runPerformanceAudit
  • Database Root Causes: Execute diagnostic SQL queries via Supabase MCP

3. Reuse Patterns & Solutions

  • Search for prior fixes or utilities in codebase
  • Library Documentation: Use Context7 MCP for up-to-date API examples and troubleshooting guides
  • Similar Issues: Use GitHub MCP to search for related issues in project history

4. Analyze Impact & Dependencies

  • Trace dependencies and side-effects
  • Frontend Impact: Use Browser Control MCP to analyze affected pages/components
  • Database Impact: Check foreign key constraints and data integrity via Supabase MCP
  • Cross-System Impact: Consider how changes affect multiple MCP domains

5. Propose & Implement Fixes

  • Specify file paths, line numbers, code snippets with clear justification
  • Clean Debugging Environment: Use mcp_browser-tools_wipeLogs before testing fixes
  • Database Fixes: Use transactions in Supabase MCP for safe schema/data changes
  • Code Changes: Use GitHub MCP for version-controlled implementation

Read the full file on GitHub · 78 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 · 78 lines · 3 tokens per session scan A ab76e4d73921

Subscribe to this mod's changes

debugging is a cursor rule published in the GitHub repository rm2thaddeus/Pixel_Detective (21 stars, last pushed 6mo ago), licensed MIT. It adds 3 tokens to every session and 860 once invoked, about $0.0000 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.