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 ricneves-ai/flowgrammers-skills --skill codigo-automacaogit clone --depth 1 https://github.com/ricneves-ai/flowgrammers-skillsWrote 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/ricneves-ai/flowgrammers-skills/codigo-automacao)<a href="https://agentmods.dev/skills/ricneves-ai/flowgrammers-skills/codigo-automacao"><img src="https://agentmods.dev/badge/skills/ricneves-ai/flowgrammers-skills/codigo-automacao/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/ricneves-ai/flowgrammers-skills/codigo-automacao"><img src="https://agentmods.dev/badge/skills/ricneves-ai/flowgrammers-skills/codigo-automacao.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 | $0.00056 | $0.02375 |
| Opus 5.5 | $0.00022 | $0.00950 |
| Sonnet 5.5 | $0.00011 | $0.00475 |
| Haiku 4.5 | $0.00006 | $0.00237 |
Grade A, and why
codigo-automacao 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 1mo 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Código, Dev & Automação (Nível PODEROSO)
Skills para engenheiros e desenvolvedores que querem acelerar com IA. Cobrindo debug sistemático, construção de APIs, Docker, testes automatizados, banco de dados, autenticação, automações no-code com Make/n8n/Zapier e engenharia avançada de prompts. Cada skill traz um framework estruturado para atacar o problema com eficiência máxima.
Início Rápido
Claude Code
/read codigo-automacao/especialista-em-debug/SKILL.md
/read codigo-automacao/construtor-de-api/SKILL.md
/read codigo-automacao/docker-compose/SKILL.md
/read codigo-automacao/automacao-de-testes/SKILL.md
/read codigo-automacao/banco-de-dados-ops/SKILL.md
/read codigo-automacao/implementacao-de-auth/SKILL.md
/read codigo-automacao/no-code-automacao/SKILL.md
/read codigo-automacao/integrador-de-webhooks/SKILL.md
/read codigo-automacao/especialista-claude-code/SKILL.md
/read codigo-automacao/engenheiro-de-prompts/SKILL.md
Cursor
Adicione em .cursor/rules/codigo-automacao.md:
Você é um engenheiro sênior especializado em debug sistemático e automação.
Ao diagnosticar bugs: sempre peça logs, stack traces e como reproduzir.
Para APIs: siga OpenAPI 3.0, documente todos os endpoints e erros possíveis.
Para testes: cobertura mínima de 80%, pirâmide de testes (unit > integration > E2E).
Codex
Inclua no AGENTS.md:
## Engenheiro Sênior Dev & Automação
Consulte codigo-automacao/ para debug, APIs, Docker, testes e automações.
Sempre proponha solução com testes. Documente decisões de arquitetura.
Visão Geral das Skills
| Skill | Pasta | Foco |
|---|---|---|
| Especialista em Debug | especialista-em-debug/ |
Diagnóstico sistemático de bugs |
| Construtor de API | construtor-de-api/ |
APIs REST e GraphQL com documentação |
| Docker Compose | docker-compose/ |
Containerização para dev e produção |
| Automação de Testes | automacao-de-testes/ |
Unit, integração, E2E com Playwright |
| Banco de Dados Ops | banco-de-dados-ops/ |
Queries, migrations, indexação, modelagem |
| Implementação de Auth | implementacao-de-auth/ |
JWT, OAuth 2.0, Supabase, Firebase |
| No-Code Automação | no-code-automacao/ |
Make, Zapier, n8n, ActivePieces |
| Integrador de Webhooks | integrador-de-webhooks/ |
Webhooks, eventos, filas de mensagens |
| Especialista Claude Code | especialista-claude-code/ |
Skills, subagentes, worktrees avançados |
| Engenheiro de Prompts | engenheiro-de-prompts/ |
Engenharia de prompts para LLMs |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- automacao-de-testes/SKILL.md 3.5 KB
- banco-de-dados-ops/SKILL.md 3.3 KB
- construtor-de-api/SKILL.md 3.3 KB
- docker-compose/SKILL.md 3.3 KB
- engenheiro-de-prompts/SKILL.md 3.6 KB
- especialista-claude-code/SKILL.md 3.5 KB
- especialista-em-debug/SKILL.md 3.7 KB
- implementacao-de-auth/SKILL.md 3.5 KB
- integrador-de-webhooks/SKILL.md 3.5 KB
- no-code-automacao/SKILL.md 3.4 KB
- references/automacao-patterns.md 7.6 KB
- references/prompt-engineering-claude.md 6.8 KB
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.
- 1mo ago First seen · 212 lines · 56 tokens per session scan A 37c5d001c295
codigo-automacao is a skill published in the GitHub repository ricneves-ai/flowgrammers-skills (116 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 2,375 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
iii-observe
Use when observing iii functions with iii.observe, writing filters, reacting to engine events, writing observable functions with owner delivery (onObserverAdded, obs.emit, obs.call), tuning local dispatch, or migrating from the deprecated registerTrigger / registerTriggerType across TypeScript, browser, Python, Rust…
iii-error-handling
Handle iii engine and SDK errors across Node, Python, Rust, and browser workers. Use when interpreting error codes, retryability, RBAC denial, timeouts, handler failures, or SDK-specific exception surfaces.
spine-perf
Find and fix performance bottlenecks — N+1 queries, missing indexes, sync bottlenecks, caching gaps. Use when asked "why is this slow", "performance issue", "optimize this endpoint", or "N+1 queries".
spine-recon
Backend reconnaissance — map all routes, middleware, models, dependencies, auth, and assess code quality for project takeover. Use when asked to "understand this backend", "map the API", or "assess code quality".
Failure Modes & Observability in Design
Ensure designs specify failure modes, timeouts, error contracts, and observability for critical flows.