systematic-debugging

A step-by-step method for finding the root cause of bugs and other unexpected software behavior before changing code.

In plain words
What is it for?
Investigating crashes, failing or flaky tests, performance problems, regressions, and incorrect results.
Why use it?
It reduces guesswork by requiring reproduction, a testable explanation, and evidence linking the symptom to its cause.

Skill for Claude CodeCodex

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 skills/clubpay/ronykit/systematic-debugging
Any agent
npx skills add clubpay/ronykit --skill systematic-debugging
Clone the repo
git clone --depth 1 https://github.com/clubpay/ronykit

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 500 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 $0.00041 $0.00500
Opus 5 $0.00020 $0.00250
Sonnet 5 $0.00008 $0.00100
Haiku 4.5 $0.00004 $0.00050

Measured 2d ago against content hash 1f5380c6e817, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

systematic-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 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.

ronyup/internal/skeleton/skills/systematic-debugging/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Debugging

Guessing creates new bugs and hides old ones. Find the root cause first.

The iron rule

No fix without a root-cause hypothesis you have confirmed with evidence.

If you cannot explain why the bug happens, you are not ready to fix it.

When to use

Any test failure, crash, wrong output, flaky test, performance regression, build failure, or integration issue — especially when under time pressure or when a previous fix didn't hold.

Phase 1 — Understand

  • Read the full error and stack trace; note file, line, and exact message.
  • Reproduce it reliably. A bug you can't reproduce, you can't verify fixed.
  • Establish the smallest reproduction and the expected vs actual behavior.

Phase 2 — Investigate

  • Form a hypothesis about the cause and predict what you'd observe if true.
  • Gather evidence: targeted logging, a debugger, git bisect, binary search by commenting/disabling, or diffing a working vs broken state.
  • Follow the data flow backward from the symptom to its origin. Question assumptions ("this can't be nil" — prove it).

Phase 3 — Fix the cause

  • Change the root cause, not the symptom. Patching where it crashed instead of where the bad value originated just moves the bug.
  • Make the smallest change that addresses the cause.

Phase 4 — Verify & prevent

  • Write a test that fails before the fix and passes after.
  • Re-run the full relevant suite to check for regressions.
  • Ask whether the same class of bug exists elsewhere.

Tactics

  • git bisect to locate the introducing commit.
  • Binary search the input/code path to isolate the trigger.
  • Add structured logging at decision points; remove it before committing.
  • For flakiness: suspect time, ordering, concurrency, and shared state; run with -race / repeated runs.

Anti-patterns

  • Trying random changes to see what sticks.
  • Adding defensive if x == nil guards without knowing why x is nil.
  • Declaring it fixed because the symptom disappeared once.

Read the full file on GitHub · 64 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. 2d ago First seen · 64 lines · 41 tokens per session scan A 1f5380c6e817

Subscribe to this mod's changes

systematic-debugging is a skill published in the GitHub repository clubpay/ronykit (38 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 41 tokens to every session and 500 once invoked, about $0.0002 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.