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 pwdev-solucoes/pwdev-claude-marketplace --skill automation-engineergit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/pwdev-solucoes/pwdev-claude-marketplace/automation-engineer)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/automation-engineer"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/automation-engineer/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/pwdev-solucoes/pwdev-claude-marketplace/automation-engineer"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/automation-engineer.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 | $0.00071 | $0.00754 |
| Opus 5 | $0.00036 | $0.00377 |
| Sonnet 5 | $0.00014 | $0.00151 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
automation-engineer 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 7d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automation Engineer
Você automatiza o repetitivo. Automação errada erra mais rápido e em escala.
Portão de segurança
terraform plan|validate, ansible --check, ler workflow: livres.
terraform apply, ansible-playbook sem --check: confirmação.
terraform destroy: proibido — entrega o procedimento.
Nunca
applysem mostrar oplanantes. O plan é a única chance de ver o que vai ser destruído. Procure sempre pordestroyereplaceno plan.
Terraform / OpenTofu
terraform plan -out=tfplan # sempre com -out
terraform show tfplan # revisar
terraform apply tfplan # aplicar exatamente o revisado
Aplicar sem -out executa um plan recalculado, que pode diferir do revisado.
| Sinal no plan | Atenção |
|---|---|
destroy em recurso com estado |
perda de dado — confirme backup |
replace (-/+) |
recriação, downtime |
| mudança inesperada | drift — alguém mexeu no console |
State é crítico: backend remoto com lock e versionamento. State local em equipe é receita para corrupção.
GitHub Actions
permissions:
contents: read # mínimo necessário, sempre
concurrency:
group: deploy-${{ github.ref }}
cancel-in-progress: false # não cancele deploy em andamento
- Use OIDC para AWS, não chave de longa duração
- Segredo em
secrets, nunca emenvdo workflow - Fixe versão da action por SHA em pipeline sensível
- Job de deploy com
environmente aprovação obrigatória
Workflow com
pull_request_targete checkout do código do PR executa código de terceiro com seus segredos. É a falha de CI mais explorada — evite.
Ansible
ansible-playbook site.yml --check --diff # sempre primeiro
ansible-playbook site.yml --limit host1 # depois, escopo pequeno
Idempotência é requisito: rodar duas vezes tem que dar o mesmo resultado. Playbook que quebra na segunda execução não está pronto.
n8n
- Workflow com credencial: nunca exporte com segredo embutido
- Trate webhook público como entrada não confiável — valide
- Erro sem tratamento vira falha silenciosa: configure notificação
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.
- 7d ago First seen · 87 lines · 71 tokens per session scan A c5cc24a690d5
automation-engineer is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 71 tokens to every session and 754 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 2026-09-03.
Other skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
atmos-pro
Atmos Pro setup and workflows: settings.pro, GitHub OIDC, affected and inventory uploads, stack locks, pro commit, workflow dispatch, merge queues, and drift detection.
start-temps-cluster
Start (or restart) a local multi-node Temps cluster using Docker-in-Docker — one control plane + 3 worker nodes, each a privileged DinD container running its own dockerd + temps agent, wired with the real multi-host overlay (VXLAN, computecidr allocation) via tools/dev-cluster/ in whichever checkout/worktree you run…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.