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 felipenalves/InvOS --skill email-profissionalgit clone --depth 1 https://github.com/felipenalves/InvOSWrote 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/felipenalves/invos/email-profissional)<a href="https://agentmods.dev/skills/felipenalves/invos/email-profissional"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/email-profissional/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/felipenalves/invos/email-profissional"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/email-profissional.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 | $0.00543 |
| Opus 5 | $0.00036 | $0.00271 |
| Sonnet 5 | $0.00014 | $0.00109 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
email-profissional 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.
What it actually says
/email-profissional — Rascunho de Email
Dependências
- Contexto do negócio:
_memoria/empresa.md - Tom de voz:
_memoria/preferencias.md
Workflow
Passo 1 — Coletar o contexto
Se o usuário não forneceu as informações necessárias, perguntar:
- "Pra quem é o email? (nome, cargo, relação com você)"
- "Qual é o objetivo? (cobrar, propor, responder, agradecer, seguir up...)"
- "Tem algo específico que precisa constar ou que precisa evitar dizer?"
Se o usuário deu o contexto de forma livre (mesmo que bagunçado), extrai o que der e prossegue.
Passo 2 — Escrever o email
Considerar:
- Tom proporcional à relação (cliente novo = mais cuidado, parceiro antigo = mais direto)
- Objetivo claro na abertura (não enterrar o pedido no final)
- Uma ação pedida por vez
- Encerramento sem redundância ("Qualquer dúvida, fico à disposição" é padrão — só usar se fizer sentido)
Estrutura:
Assunto: [linha de assunto direta, sem clicbait]
[Nome],
[Parágrafo 1 — contexto ou referência ao último contato]
[Parágrafo 2 — o ponto principal ou o pedido]
[Parágrafo 3 — próximo passo, se houver]
[Assinatura]
[Nome do usuário, de _memoria/empresa.md]
Passo 3 — Apresentar opções de tom (quando fizer sentido)
Se o assunto for delicado (cobrança, feedback negativo, recusa), oferecer 2 versões:
- Versão A: mais direta
- Versão B: mais suave
Deixar o usuário escolher.
Regras
- Tom segue
_memoria/preferencias.md - Nunca usar linguagem corporativa genérica sem necessidade
- Assunto do email deve ser específico e descritivo, não vago ("Seguimento", "Proposta")
- Se for um email de cobrança, ser direto mas sem agressividade
- Se for resposta a algo, citar o contexto na primeira linha
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 · 71 lines · 71 tokens per session scan A 03f7cc052444
email-profissional is a skill published in the GitHub repository felipenalves/InvOS (5 stars, last pushed 6d ago), licensed MIT. It adds 71 tokens to every session and 543 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 2026-08-31.
Other skills, from other repositories
hindsight-architect
Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code.
create-agent
Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.
hindsight-docs
Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
hindsight-memory
Long-term memory for the agent via Hindsight. Use to recall relevant past context before answering, retain durable facts as you learn them, and reflect over accumulated memory for the "why" behind a decision. Load whenever continuity across sessions matters — the user refers to earlier work, states a lasting…
hindsight-recall
Search long-term memory for relevant context from past coding sessions using Hindsight MCP tools.