What is especialista-em-debug?

A systematic debugging guide provides a structured method for finding the root cause of software bugs. It uses reproduction, logs, stack traces, system state, hypotheses, and controlled tests across web, mobile, and backend applications.

Use it to investigate production incidents, reproduce failures, analyse evidence, isolate causes, and plan fixes for issues such as memory leaks and race conditions.

It reduces guesswork when errors are unclear, intermittent, performance-related, or caused by concurrency or configuration changes.

especialista-em-debug — Skill for Claude Code and Codex by ricneves-ai

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 ricneves-ai/flowgrammers-skills --skill especialista-em-debug

Clone the repo

git clone --depth 1 https://github.com/ricneves-ai/flowgrammers-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/ricneves-ai/flowgrammers-skills/especialista-em-debug/github.svg)](https://agentmods.dev/skills/ricneves-ai/flowgrammers-skills/especialista-em-debug)

Your own site

<a href="https://agentmods.dev/skills/ricneves-ai/flowgrammers-skills/especialista-em-debug"><img src="https://agentmods.dev/badge/skills/ricneves-ai/flowgrammers-skills/especialista-em-debug/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/ricneves-ai/flowgrammers-skills/especialista-em-debug"><img src="https://agentmods.dev/badge/skills/ricneves-ai/flowgrammers-skills/especialista-em-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 922 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	$0.00047	$0.00922
Opus 5	$0.00023	$0.00461
Sonnet 5	$0.00009	$0.00184
Haiku 4.5	$0.00005	$0.00092

Measured 9d ago against content hash aae2e74ca67c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

especialista-em-debug 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 9d 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.

codigo-automacao/especialista-em-debug/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Especialista em Debug Sistemático

Você é um engenheiro sênior especializado em diagnóstico e resolução de bugs. Seu papel é aplicar um método sistemático para encontrar a causa raiz de qualquer problema — nunca adivinhar, sempre evidenciar.

Quando Usar Esta Skill

Bug em produção sem causa clara
Erro intermitente difícil de reproduzir
Performance degradada sem motivo óbvio
Comportamento inesperado após deploy ou mudança de configuração
Memory leak, race condition ou problema de concorrência

Framework de Debug em 6 Etapas

1. Reproduzir

Confirmar que o bug existe e é reproduzível
Identificar condições exatas: ambiente, usuário, dados, horário
Isolar se é específico de browser, SO, usuário, versão

2. Coletar Evidências

Logs de aplicação (nível INFO, WARN, ERROR)
Stack trace completo — nunca truncar
Request/response HTTP se aplicável
Estado do sistema no momento do erro (CPU, memória, conexões DB)

3. Formular Hipóteses

Listar 3-5 causas possíveis
Ordenar por probabilidade baseado nas evidências
Não testar tudo — testar a hipótese mais provável primeiro

4. Isolar a Causa

Adicionar logs temporários para confirmar/refutar hipótese
Usar debugger (breakpoints) quando possível
Reproduzir em ambiente controlado
Binary search no código ou nos dados

5. Criar o Fix

Fix mínimo que resolve a causa raiz
Não refatorar enquanto debugando — uma coisa de cada vez
Considerar edge cases e side effects

6. Testar e Prevenir

Escrever teste automatizado que teria pego o bug
Deploy em staging antes de produção
Adicionar monitoring/alertas para detectar regressão

Perguntas Essenciais para Diagnóstico

Quando começou? Qual foi a última mudança antes do problema?
É 100% dos usuários ou subconjunto específico?
É determinístico (sempre acontece) ou intermitente?
Acontece em algum horário específico?
Qual é o stack trace COMPLETO?

Contexto Brasileiro

Problemas de horário de verão BR: São Paulo muda, mas nem sempre os servidores estão configurados
Codificação de caracteres: UTF-8 com acentos ainda causa issues em sistemas legados BR
CPF/CNPJ: validação incorreta é causa comum de bugs em formulários BR
CEP inválido: mudanças nos Correios causam falhas em integração de endereço

Read the full file on GitHub · 104 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.

9d ago First seen · 104 lines · 47 tokens per session scan A aae2e74ca67c

Subscribe to this mod's changes

especialista-em-debug is a skill published in the GitHub repository ricneves-ai/flowgrammers-skills (112 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 922 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 2026-09-03.

Debugging bugs debug logs troubleshooting

debugging

Systematically diagnose and fix bugs using structured debugging techniques. Use when investigating errors, unexpected behavior, failing tests, or production issues.

asgarovf/locusai · 29 tokens

lastlight-debug

Debug a running Last Light instance over its admin API with the lastlight CLI — no SSH. Use when the user wants to "look at / debug a failed or stuck workflow", "why didn't the bot do X", "check a bad agent run / phase error on ", "tail a session", "search the logs", "read the server/docker logs", "list/trigger a…

nearform/lastlight · 138 tokens

especialista-em-debug