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 security-audit-methodgit 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/security-audit-method)<a href="https://agentmods.dev/skills/joaoguirunas/team-os/security-audit-method"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/security-audit-method/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/security-audit-method"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/security-audit-method.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 | $0.00074 | $0.01469 |
| Opus 5.5 | $0.00030 | $0.00588 |
| Sonnet 5.5 | $0.00015 | $0.00294 |
| Haiku 4.5 | $0.00007 | $0.00147 |
Grade A, and why
security-audit-method 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Método de auditoria de segurança
Base comum dos sete agentes da squad Security. Os especialistas auditam com o método da sua área; esta skill define como todo achado é escrito, classificado e fechado, para que o security-qa julgue tudo com a mesma régua.
1. Escopo autorizado (antes de qualquer comando)
- A squad audita só o projeto em que está instalada: o código do repositório, o banco e os serviços do próprio usuário.
- Teste ativo (requisição montada, payload, varredura de rede) só em ambiente local ou de staging do próprio usuário, com escopo escrito na story. Produção: só leitura passiva (headers, configuração pública, o que o navegador de qualquer visitante já vê), salvo autorização escrita do usuário na story, com janela e limite.
- Nunca contra sistema de terceiro, nunca ataque de negação de serviço, nunca tentativa de login com credencial alheia, nunca exfiltrar dado real para "provar" um achado. Prova de conceito descreve a exploração; não a executa contra dado de pessoa real.
- Escopo fica escrito no topo do relatório: o que foi olhado, como, e o que ficou de fora.
2. Escala de severidade
| Severidade | Quando | Exemplos |
|---|---|---|
| CRITICAL | Exploração direta, sem pré-requisito, com dano amplo | segredo privado alcançável pelo cliente ou no repositório; service_role no navegador; tabela de dados sem RLS ou com UPDATE/DELETE aberto; injeção de SQL com acesso a dado; bypass de autenticação |
| HIGH | Exploração plausível com dano sério, ou com pré-requisito simples | leitura aberta de dado pessoal; IDOR/BOLA (trocar o id na URL e ver dado de outro); autorização por campo que o cliente edita (user_metadata, papel no body); prompt de sistema com dado da requisição numa chamada com tools; bucket privado aberto; dependência com CVE explorável no caminho usado |
| MEDIUM | Precisa de condição extra ou o dano é limitado | CSRF em ação que muda estado; ausência de rate limit em login ou formulário; erro vazando stack trace ou caminho interno; prompt de sistema com dado do usuário sem tools; CSP ausente em página com conteúdo de terceiros |
| LOW | Endurecimento, sem exploração clara | header de segurança faltando em página estática; versão do servidor exposta |
| INFO | Boa prática, sem risco hoje | sugestão de organização, monitoramento |
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 · 80 lines · 74 tokens per session scan A 6495d899e883
security-audit-method is a skill published in the GitHub repository joaoguirunas/team-os (4 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,469 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 2026-10-08.
Other skills, from other repositories
jsonl-log-analyzer
Analyze large JSONL log files using schema-aware partitioned analysis. Discovers field schema, generates tailored jq extraction recipes, and orchestrates parallel chunk analysts with synthesis. Use when processing JSONL logs exceeding context limits, performing log analytics, or investigating incident logs.
orchestration-patterns
Apply proven orchestration patterns for agent teams including parallel specialists, pipelines, swarms, research+implementation, plan approval, and multi-file refactoring. Use when choosing a team structure, designing workflows, or implementing specific coordination patterns.
task-system
Manage shared task lists for agent teams including creating tasks, setting dependencies, claiming work, and tracking progress. Use when creating work items, building task pipelines, coordinating task ownership, or managing task dependencies.
spawn-backends
Configure how teammate agents run including in-process, tmux, and iTerm2 backends. Use when choosing a display mode, setting up split panes, troubleshooting backend issues, or configuring teammateMode.
error-handling
Debug and recover from agent team errors including common errors, hooks for quality gates, known limitations, and recovery strategies. Use when encountering team errors, enforcing quality gates with hooks, understanding limitations, or debugging agent issues.
messaging
Send messages between agents using SendMessage including direct messages, broadcasts, shutdown requests/responses, and plan approvals. Use when communicating between agents, understanding message formats, or handling structured protocol messages.