agentmods.dev

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.

In plain words
What is it for?
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.
Why use it?
It reduces guesswork and prevents random changes that can hide the real problem or create new ones.

Skill for Claude CodeCodex

64 2mo ago A scan 86 tokens original MIT
View the source file AlekseiUL/sprut-agent-kit
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/alekseiul/sprut-agent-kit/systematic-debugging
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.

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. 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 $0.00086 $0.01047
Opus 5 $0.00043 $0.00524
Sonnet 5 $0.00017 $0.00209
Haiku 4.5 $0.00009 $0.00105

Measured 2d ago against content hash 743e1ce9f9cd, 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.

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:

  1. Прочитай ошибку целиком

    • Не пропускай стектрейсы и warnings
    • Часто ответ прямо в тексте ошибки
    • Запиши: файл, строка, код ошибки

  2. Воспроизведи

    • Можешь повторить проблему?
    • Какие точные шаги?
    • Если не воспроизводится - собирай больше данных, не гадай

  3. Что изменилось?

    • git diff, последние коммиты
    • Обновление платформы? (проверь версию)
    • Новые зависимости, конфиг?
    • memory/progress-log.md - что делалось недавно

  4. Проследи поток данных Для многокомпонентных систем (крон → gateway → агент → tool → результат):

    На каждом стыке:
- Что входит?
- Что выходит?
- Где ломается?

Фаза 2: Анализ паттерна

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

Фаза 3: Гипотеза и тест

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

Фаза 4: Реализация фикса

  1. Фикси причину, не симптом
  2. Одно изменение за раз
  3. Проверь - проблема ушла? Ничего другого не сломалось?
  4. Запиши - bash scripts/progress-log.sh + daily notes если важное
  5. 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.

  1. 2d 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 (64 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,047 once invoked, about $0.0004 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.

Debuggingagent-skillsai-agentsai-assistantautomationclaude-codeclaudeclaw
Related

Other skills, from other repositories

agent-code-analyzer

Agent skill for code-analyzer - invoke with $agent-code-analyzer.

ruvnet/ruflo · 19 tokens

agent-collective-intelligence-coordinator

Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator.

ruvnet/ruflo · 29 tokens

agent-payments

Agent skill for payments - invoke with $agent-payments.

ruvnet/ruflo · 15 tokens

add-resend

Add Resend (email) channel integration via Chat SDK.

nanocoai/nanoclaw · 16 tokens

add-macos-statusbar

Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.

nanocoai/nanoclaw · 49 tokens

develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.

netease-youdao/LobsterAI · 64 tokens