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 inhabitants/sapiens-mcp --skill primeiros-passosgit clone --depth 1 https://github.com/inhabitants/sapiens-mcpWrote 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/inhabitants/sapiens-mcp/primeiros-passos)<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/primeiros-passos"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/primeiros-passos/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/inhabitants/sapiens-mcp/primeiros-passos"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/primeiros-passos.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 | $0.00053 | $0.00792 |
| Opus 5.5 | $0.00021 | $0.00317 |
| Sonnet 5.5 | $0.00011 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
primeiros-passos 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 4d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Primeiros passos e armadilhas
A porta de entrada
Primeiro contato, ou "o que você faz?" / "como começo?": chame sapiens_meta action=start e mostre o resultado NA SUA VOZ. Sem login ele ensina a conectar; logado, traz saldo e os primeiros poderes com exemplo pronto.
Logo após um login que deu certo, chame start na sequência. O recém-chegado não sabe o que pedir: guie a primeira jogada sem ele precisar perguntar.
Não despeje a lista inteira de tools. O start guia.
As quatro armadilhas
0. Vídeo longo volta pending, e isso é sucesso. Um sapiens_video action=create que demora mais que a espera síncrona responde {success: true, pending: true} SEM url: o pedido foi aceito, já cobrou, e o servidor termina sozinho. NÃO gere de novo (cobraria duas vezes): acompanhe com action=status no imageId, ou olhe a galeria depois.
1. Timeout que já cobrou. Toda geração SÍNCRONA (imagem pesada, artigo, mega-gráfico, carrossel) pode estourar o teto de ~120s do cliente e voltar 'Timeout' MESMO tendo gerado e debitado. Nunca repita às cegas. Confira antes onde o resultado teria caído:
| O que gerou | Onde conferir |
|---|---|
| imagem | sapiens_gallery action=list |
| artigo do perfil | sapiens_write action=list |
| carrossel | sapiens_carrossel action=list |
2. Disjuntor anti-loop. Três falhas seguidas no MESMO tool fazem o cliente marcar o servidor como "unreachable" por ~56s. Parece que "o MCP caiu", mas foi argumento faltando. Quando um tool volta erro de validação ("exige X", "falta Y"), LEIA o erro e refaça a chamada COM o que falta. Nunca repita a chamada idêntica que falhou.
3. Saldo. Antes de gerar algo caro (imagem, música, vídeo), cheque com sapiens_meta action=credits ou action=subscription. Saldo baixo, avise ANTES de gastar. Vídeo é o mais caro da casa: confirme com a pessoa antes de disparar.
4. Sessão. "sessionToken expirado" significa refazer login: sapiens_meta action=login com o código de sapiensinteticos.com/conectar-claude.
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.
- 4d ago Changed · +1 lines dd7f45502753
- 26d ago First seen · 40 lines · 53 tokens per session scan A d64fc2b6f7d1
primeiros-passos is a skill published in the GitHub repository inhabitants/sapiens-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 792 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 2026-09-28.
Other skills, from other repositories
memory-safety-c-cpp
Reference vocabulary for memory-safety vulnerabilities in native C/C++ code — bug-class taxonomy, common arithmetic patterns that lead to corruption, dispatch-family discipline, type-confusion idioms, use-after-free patterns, and exploitability factors. Read when analyzing, hypothesizing, designing harnesses for, or…
RootCauseAnalysis
Structured incident investigation using Five Whys, Fishbone, blameless Postmortem, Fault Tree, Kepner-Tregoe, and FMEA — traces failures to systemic root causes rather than blaming humans. USE WHEN root cause, RCA, 5 whys, fishbone, postmortem, incident analysis, fault tree, why does this keep failing, blameless…
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
Vitals
Read-only macOS performance inspection: a deterministic CLI gathers the numbers, Interpretation.md turns them into a diagnosis instead of a data dump.
agent-incident-postmortem
Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonomously. Use when asked to write up an AI incident, analyse why an agent did something wrong, or produce corrective…
agent-design-review
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools…