What is systematic-debugging?

A step-by-step method for finding the cause of bugs, errors, and unexpected behaviour before suggesting a fix. It starts with the full error, reproduction steps, recent changes, and the path data takes through connected parts of a system.

Use it when a script crashes, a scheduled job fails, a service stops responding, a container drops, or a feature that worked before behaves differently.

It reduces guesswork and prevents random changes that can hide the real problem or create new ones.

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

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 AlekseiUL/sprut-agent-kit --skill systematic-debugging

Clone the repo

git clone --depth 1 https://github.com/AlekseiUL/sprut-agent-kit

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/alekseiul/sprut-agent-kit/systematic-debugging/github.svg)](https://agentmods.dev/skills/alekseiul/sprut-agent-kit/systematic-debugging)

Your own site

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

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,047 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	$0.00086	$0.01047
Opus 5.5	$0.00034	$0.00419
Sonnet 5.5	$0.00017	$0.00209
Haiku 4.5	$0.00009	$0.00105

Measured 1mo ago against content hash 743e1ce9f9cd, 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.

skills/systematic-debugging/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Систематическая отладка

Железное правило

НИКАКИХ ФИКСОВ БЕЗ ПОНИМАНИЯ ПРИЧИНЫ

Рандомные фиксы тратят время и создают новые баги. Если не прошёл Фазу 1 - нельзя предлагать решения.

Когда использовать

Любая техническая проблема:

Крон не запустился / выдал ошибку
Скрипт падает
Gateway не отвечает
Docker контейнер упал
Память не ищет нужное
Бот не отправляет сообщения
Любое "раньше работало, теперь нет"

Особенно когда: под давлением, "очевидный фикс" напрашивается, уже пробовал 2+ решения.

Четыре фазы

Фаза 1: Расследование причины

ПЕРЕД любым фиксом:

Прочитай ошибку целиком
- Не пропускай стектрейсы и warnings
- Часто ответ прямо в тексте ошибки
- Запиши: файл, строка, код ошибки
Воспроизведи
- Можешь повторить проблему?
- Какие точные шаги?
- Если не воспроизводится - собирай больше данных, не гадай
Что изменилось?
- git diff, последние коммиты
- Обновление платформы? (проверь версию)
- Новые зависимости, конфиг?
- memory/progress-log.md - что делалось недавно
Проследи поток данных Для многокомпонентных систем (крон → gateway → агент → tool → результат):
```
На каждом стыке:
- Что входит?
- Что выходит?
- Где ломается?
```

Фаза 2: Анализ паттерна

Найди рабочий пример - похожий скрипт/крон который работает
Сравни - что отличается между рабочим и сломанным?
Проверь зависимости - всё ли на месте (docker, npm, пути, права)?

Фаза 3: Гипотеза и тест

Сформулируй гипотезу - "Я думаю причина в X потому что Y"
Минимальный тест - ОДНО изменение, ОДНА переменная
Проверь - сработало → Фаза 4. Нет → новая гипотеза
НЕ лепи фиксы поверх - если не сработало, откати и думай заново

Фаза 4: Реализация фикса

Фикси причину, не симптом
Одно изменение за раз
Проверь - проблема ушла? Ничего другого не сломалось?
Запиши - bash scripts/progress-log.sh + daily notes если важное
Если 3+ фикса не сработали - СТОП. Проблема архитектурная. Обсуди с Алексеем.

Read the full file on GitHub · 103 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.

1mo ago First seen · 103 lines · 86 tokens per session scan A 743e1ce9f9cd

Subscribe to this mod's changes

systematic-debugging is a skill published in the GitHub repository AlekseiUL/sprut-agent-kit (65 stars, last pushed 4mo ago), licensed MIT. It adds 86 tokens to every session and 1,047 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 2026-08-30.

Claude Code Debugging agent-skills ai-agents ai-assistant automation claudeclaw