What is systematic-debugging?

A step-by-step method for investigating technical problems such as stack traces, failed tests, production bugs, and unexpected behavior. It requires collecting evidence and identifying the root cause before changing code.

Use it to read errors, inspect the relevant code and configuration, trace related definitions and usages, form a hypothesis, and then choose a verified fix.

It reduces guesswork and avoids quick fixes that hide the real problem or introduce new failures.

systematic-debugging — Skill for Claude Code and Codex by rolandbrecht

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.

Any agent

npx skills add rolandbrecht/agent-skills --skill systematic-debugging

Clone the repo

git clone --depth 1 https://github.com/rolandbrecht/agent-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rolandbrecht/agent-skills/systematic-debugging/github.svg)](https://agentmods.dev/skills/rolandbrecht/agent-skills/systematic-debugging)

Your own site

<a href="https://agentmods.dev/skills/rolandbrecht/agent-skills/systematic-debugging"><img src="https://agentmods.dev/badge/skills/rolandbrecht/agent-skills/systematic-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rolandbrecht/agent-skills/systematic-debugging"><img src="https://agentmods.dev/badge/skills/rolandbrecht/agent-skills/systematic-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,018 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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.01018
Opus 5.5	$0.00026	$0.00407
Sonnet 5.5	$0.00013	$0.00204
Haiku 4.5	$0.00006	$0.00102

Measured 1mo ago against content hash 29344ce48cdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

systematic-debugging/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Debugging

Overview

Random fixes waste time and create new bugs. Quick patches mask underlying issues. As an AI agent, it is tempting to rapidly guess the solution based on symptoms because it is fast. You must resist this temptation.

Core principle: ALWAYS find the root cause before attempting fixes. The Iron Law: NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.

When to Use

Use for ANY technical issue:

Test failures
Bugs in production or local development
Build or CI pipeline failures
Unexplained performance issues

Do not skip this process even if:

The issue seems "simple" or "obvious"
You are under time pressure
The user asks for a "quick fix"

Phase 1: Planning (Root Cause Investigation)

BEFORE attempting ANY code modification or fix:

Information Gathering (Do Not Guess)
- Read the error message and stack trace completely. Note the exact file paths and line numbers.
- Use view_file to read the surrounding code where the error occurred.
- Use grep_search to find definitions, usages, or configurations related to the failing components.
- Never assume you know what a file contains without checking or listing its directory.
Reproduce and Isolate
- Can you trigger the bug reliably? If there isn't an existing test, write a minimal, standalone reproduction script (e.g., repro.py or .js in /tmp/) using write_to_file and then execute it via run_command.
- If you cannot reproduce it locally, you must gather more data. Do not guess the fix.
Map the Boundaries (Multi-Component Systems)
- If the system has multiple layers (e.g., Frontend → API → Database), do not guess which layer failed.
- Inject telemetry temporarily: Use replace_file_content to add console.log, print(), or logger statements at the boundary of each component.
- Run the system once to see exactly what data entered and exited each layer.

Phase 2: Execution (Hypothesis & Minimal Fix)

Read the full file on GitHub · 97 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 97 lines · 64 tokens per session scan A 29344ce48cdd

Subscribe to this mod's changes

systematic-debugging is a skill published in the GitHub repository rolandbrecht/agent-skills (4 stars, last pushed 29d ago), licensed MIT. It adds 64 tokens to every session and 1,018 once invoked, about $0.0003 per session on Opus 5.5. 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.

Debugging agent-skills agents agentskills ai ai-agent-tools ai-agents

systematic-debugging

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Systematic Debugging

Overview

When to Use

Phase 1: Planning (Root Cause Investigation)

Phase 2: Execution (Hypothesis & Minimal Fix)

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

cocoreview

meter-reconcile

stall-reset

stall-status

stall-thresholds

stall