root-cause-debugging

root-cause-debugging is a cursor rule for Cursor from Oriolshhh/runware-image-mcp. It costs 10 tokens per session (546 once invoked), scanned A, original, MIT.

A debugging method that finds the actual cause of a failure through reproduction, controlled experiments, a minimal fix, and regression testing.

In plain words
What is it for?
It is used for crashes, regressions, failing tests, races, data corruption, incorrect output, and unexpected performance changes.
Why use it?
It reduces guess-and-check patches and helps distinguish deterministic bugs from flaky or environment-specific failures.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It is used for crashes, regressions, failing tests, races, data corruption, incorrect output, and unexpected performance changes.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/oriolshhh/runware-image-mcp/root-cause-debugging
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.

Clone the repo
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp

Made for: Cursor.

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 root-cause-debugging

README.md
[![agentmods](https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/root-cause-debugging/github.svg)](https://agentmods.dev/rules/oriolshhh/runware-image-mcp/root-cause-debugging)
Your own site
<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/root-cause-debugging"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/root-cause-debugging/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for root-cause-debugging

Your own site · 80×15
<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/root-cause-debugging"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/root-cause-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 546 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00010 $0.00546
Opus 5 $0.00005 $0.00273
Sonnet 5 $0.00002 $0.00109
Haiku 4.5 $0.00001 $0.00055

Measured 5d ago against content hash d1959bb77b01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

root-cause-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 5d 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/root-cause-debugging.mdc · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: root-cause-debugging

Root-Cause Debugging

Purpose

Prevent guess-and-check patches by turning debugging into a bounded sequence of reproduction, isolation, falsification, correction, and verification.

When to use it

  • Bugs, regressions, crashes, failing or flaky tests, races, data corruption, incorrect output, and unexpected performance changes.
  • Any time the proposed fix precedes a demonstrated causal explanation.

Instructions

  1. Write expected versus observed behavior and capture the exact reproduction.
  2. Establish baseline frequency and environment; distinguish deterministic, intermittent, and environment-dependent failures.
  3. Minimize the reproducer and locate the narrowest failing boundary.
  4. Build an evidence ledger with four columns: observation, hypothesis, discriminating experiment, result.
  5. Rank hypotheses and test one at a time. Predict both supporting and rejecting results before the experiment.
  6. Once evidence supports a root cause, write a regression test at the lowest stable layer that exposes the causal behavior.
  7. Apply the minimal fix; rerun the original reproducer, regression, neighboring tests, and configured gates.
  8. Count each reproduce→investigate→experiment→fix→verify pass as one iteration and obey the current debug-loop.max_iterations value.

Output format

A concise debug report: symptom, reproduction, environment, evidence ledger, root cause, rejected hypotheses, fix, regression test, iteration count, exact verification results, residual risk, and next experiment if unresolved.

Anti-patterns

  • Editing before reproducing.
  • Treating the first plausible explanation as proven.
  • Combining multiple speculative changes in one experiment.
  • Adding sleeps/retries without explaining the underlying timing or reliability issue.
  • Weakening tests or suppressing errors to produce green output.
  • Continuing beyond the configured iteration limit.

Read the full file on GitHub · 59 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. 5d ago First seen · 59 lines · 10 tokens per session scan A d1959bb77b01

Subscribe to this mod's changes

root-cause-debugging is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 546 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 2026-09-03.