debugging-protocol

debugging-protocol is a cursor rule for coding agents from boparaiamrit/skills-by-amrit. It costs 12 tokens per session (331 once invoked), scanned A, original, MIT.

A step-by-step protocol for investigating bugs and unexpected software behavior.

In plain words
What is it for?
Use it to investigate errors, compare expected and actual behavior, inspect recent changes, add regression tests, and verify the complete test suite.
Why use it?
It keeps debugging focused on reproducing the problem, testing ranked explanations, making a minimal fix, and checking for regressions.

Cursor rule

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/boparaiamrit/skills-by-amrit/debugging-protocol
Clone the repo
git clone --depth 1 https://github.com/boparaiamrit/skills-by-amrit

Wrote 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.

agentmods badge for debugging-protocol

README.md
[![agentmods](https://agentmods.dev/badge/rules/boparaiamrit/skills-by-amrit/debugging-protocol.svg)](https://agentmods.dev/rules/boparaiamrit/skills-by-amrit/debugging-protocol)
Your own site
<a href="https://agentmods.dev/rules/boparaiamrit/skills-by-amrit/debugging-protocol"><img src="https://agentmods.dev/badge/rules/boparaiamrit/skills-by-amrit/debugging-protocol.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 331 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 $0.00012 $0.00331
Opus 5 $0.00006 $0.00166
Sonnet 5 $0.00002 $0.00066
Haiku 4.5 $0.00001 $0.00033

Measured 3d ago against content hash cdc2c76d7555, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debugging-protocol 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 3d 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/debugging-protocol.mdc · 44 lines

What it actually says

Debugging Protocol

When debugging an issue, follow the scientific method:

Step 1: Reproduce

  • Understand the expected vs actual behavior
  • Identify exact error messages and stack traces
  • Determine when the issue started (check git log)

Step 2: Hypothesize

  • Form 3-5 ranked hypotheses based on symptoms
  • For each: rationale, test to prove/disprove, evidence needed
  • Start with the most likely hypothesis

Step 3: Investigate

  • Search for error messages in the codebase
  • Trace the execution path from entry to failure
  • Check recent changes: git diff HEAD~5
  • Read related files completely (don't skim)
  • Check tests — are tests passing incorrectly?

Step 4: Fix

  • Apply the minimal correct fix — fewest lines changed
  • Do NOT refactor while debugging
  • Add a comment explaining WHY if the fix is non-obvious
  • Write a regression test that would have caught this bug

Step 5: Verify

  • Run the full test suite (not just the new test)
  • Check for ripple effects — did the fix break anything else?
  • Verify the original symptom is resolved

NEVER

  • Fix symptoms without understanding root cause
  • Apply multiple changes at once to "see what sticks"
  • Skip writing a regression test
  • Expand scope during debugging (note other issues, fix them separately)
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. 3d ago First seen · 44 lines · 12 tokens per session scan A cdc2c76d7555

Subscribe to this mod's changes

debugging-protocol is a cursor rule published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 331 once invoked, about $0.0001 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.