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.
npx skills add joaoguirunas/team-os --skill dev-debugginggit clone --depth 1 https://github.com/joaoguirunas/team-osWrote 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.
[](https://agentmods.dev/skills/joaoguirunas/team-os/dev-debugging)<a href="https://agentmods.dev/skills/joaoguirunas/team-os/dev-debugging"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/dev-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.
<a href="https://agentmods.dev/skills/joaoguirunas/team-os/dev-debugging"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/dev-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00084 | $0.02093 |
| Opus 5.5 | $0.00034 | $0.00837 |
| Sonnet 5.5 | $0.00017 | $0.00419 |
| Haiku 4.5 | $0.00008 | $0.00209 |
Grade A, and why
dev-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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Depuração — da falha à causa raiz, com prova
Depurar é eliminar hipóteses com evidência, não tentar consertos até um "pegar". Vale para teste vermelho, build quebrado, bug em produção e comportamento estranho sem erro nenhum.
Regra de parada
Quando algo inesperado acontece:
- Pare de adicionar feature ou mudar código não relacionado — erro em cima de erro contamina o diagnóstico.
- Guarde a evidência antes de mexer: mensagem completa, stack trace, log com horário, comando exato, commit (
git rev-parse HEAD), dado de entrada. - Siga as cinco etapas abaixo em ordem. Pular etapa é o que transforma 20 minutos em uma tarde.
- Só volte ao trabalho anterior depois do
/verify-before-done.
1. Reproduzir
Sem reprodução não há como saber se a correção funcionou. Escreva os passos mínimos e fixe as três variáveis:
| Variável | O que anotar |
|---|---|
| Passos | Sequência exata, do estado limpo até a falha (comando, clique, requisição) |
| Ambiente | Versões (Node, navegador, SO, dependências do lockfile), variáveis de ambiente, flags, local × CI × produção |
| Dado | Registro, payload ou arquivo que dispara a falha — e se ela some com outro dado |
Para teste: rode só o teste que falha, isolado e em série (sem paralelismo), com saída detalhada — use o comando de teste do próprio repositório.
Não reproduz? Classifique antes de desistir:
- Tempo (corrida, timeout) → carimbo de tempo nos logs, atraso artificial para alargar a janela, rodar sob carga ou concorrência.
- Ambiente → comparar versões e variáveis lado a lado; tentar no CI, que é o ambiente limpo.
- Estado → estado vazando entre testes ou requisições (global, singleton, cache); rodar o cenário isolado × depois de outros.
- Aleatório de fato → log defensivo no ponto suspeito, alerta pela assinatura do erro, registrar as condições observadas e voltar quando repetir. Não "corrija" o que não reproduziu — relate como hipótese.
2. Localizar
Descubra onde antes de perguntar por quê.
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.
- 2d ago First seen · 133 lines · 84 tokens per session scan A 9f13811bfc62
dev-debugging is a skill published in the GitHub repository joaoguirunas/team-os (5 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 2,093 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 2026-10-22.
Other skills, from other repositories
fixing-bugs
Fix a bug using strict TDD — UNDERSTAND → REPRODUCE (RED) → VERIFY RED → FIX → VERIFY GREEN → VALIDATE → REFACTOR. Use when the user reports a bug, asks to fix something, mentions a Sentry/error/regression, or pastes a stack trace. Bugs require a failing test that proves the bug existed before any code change. For…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
triage-issue
Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report.
refactor-ops
Safe refactoring patterns - extract, rename, restructure with test-driven methodology and dead code detection. Use for: refactor, refactoring, extract function, extract component, rename, move file, restructure, dead code, unused imports, code smell, duplicate code, long function, god object, feature envy, DRY…
pair-programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
python-testing
Expert in Python testing with pytest and test-driven development.