debug

A set of instructions for debugging software. Debugging means finding the specific cause of a failure before changing the code.

In plain words
What is it for?
Use it during debugging to inspect failures, investigate similar solved issues, understand relevant architecture, and propose a fix.
Why use it?
It asks the assistant to collect more evidence after failed tests, explain its reasoning, consider architectural causes, and present fixes for validation.

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/inakianduaga/clockify-mcp/debug
Clone the repo
git clone --depth 1 https://github.com/inakianduaga/clockify-mcp

Made for: Cursor.

Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 383 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 $0.00005 $0.00383
Opus 5 $0.00003 $0.00192
Sonnet 5 $0.00001 $0.00077
Haiku 4.5 $0.00001 $0.00038

Measured 2d ago against content hash 581a9649b09d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug 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 2d 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/debug.mdc · 28 lines

What it actually says


description: Include these rules while DEBUGGING. globs: alwaysApply: true

  • Whenever you fail with any test result, always add more context using and debug the issue effectively first, then when you have complete information move towards a fix.
  • Explain your OBSERVATIONS and then give your REASONINGS to explain why this is EXACTLY the issue and not anything else.
  • If you aren't sure, first get more OBSERVATIONS by adding more context to the issue so you exactly and specifically know what's wrong. Additionally you can seek if required.
  • Understand architecture using (defined in implement.mdc ) relevant to the issue.
  • Use to think of all possible causes like architectural misalignment, design flaw rather than just a bug, etc.
  • Look for similar patterns already solved elsewhere in the codebase in @error-documentation.mdc and if needed
  • Present your fix using for validation.
  • Start modifying code to update and fix things using and (both defined in implement.mdc ).
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. 2d ago First seen · 28 lines · 5 tokens per session scan A 581a9649b09d

Subscribe to this mod's changes

debug is a cursor rule published in the GitHub repository inakianduaga/clockify-mcp (14 stars, last pushed 1y ago), licensed MIT. It adds 5 tokens to every session and 383 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.