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 pontesgit 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/pontes)<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/pontes"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/pontes/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/pontes"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/pontes.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 | $0.00193 | $0.03591 |
| Opus 5.5 | $0.00077 | $0.01436 |
| Sonnet 5.5 | $0.00039 | $0.00718 |
| Haiku 4.5 | $0.00019 | $0.00359 |
Grade A, and why
pontes 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pontes: gerar com a sua chave e trazer pro acervo
O que é uma ponte
O Sapiens é uma das pontes, não um muro. A pessoa monta o personagem aqui (ficha, passaporte, referências) e gera a peça ONDE TEM CRÉDITO: Kie, fal, Magnific, Sogni, Krea, Replicate, a própria placa. A peça volta pro acervo dela como NATIVA, com motor, prompt, custo real e personagem na ficha, custo 0 em Sinapses. O portfólio dela cresce aqui; o dinheiro dela sai de onde ela já pôs.
São duas portas lado a lado, e nenhuma é a reserva da outra: Sinapse (sapiens_image, sapiens_video) é pra quem não quer configurar nada; a chave própria é pra quem já tem crédito num provedor, e aí a casa não cobra nada em cima: ela paga o preço do provedor, sem margem nossa. Quando a pessoa tem chave configurada, ofereça as duas.
A regra da chave, sem exceção: a chave do provedor NUNCA passa pelo Sapiens. Não vai em arg de tool, não vai em prompt, não vai colada no chat. Ela mora na máquina da pessoa (o campo do plugin do Claude Code ou da extensão do Claude Desktop, ou o env do config do cliente MCP com FAL_KEY, KIE_API_KEY; um conector MCP do provedor ligado na conversa; o SDK dela) e quem chama o motor é um processo DA MÁQUINA DELA: o sapiens-mcp instalado (sapiens_pontes) ou o harness dela. O Sapiens entra ANTES (a ficha) e DEPOIS (o ingest). Se a pessoa colar a chave no chat por engano, diga pra ela gerar uma chave nova no provedor e pôr a nova no lugar dela (o comoConfigurar da sapiens_pontes action=balcoes diz onde), e siga sem usar o valor.
Passo 1: descobrir onde a pessoa tem crédito
sapiens_meta action=pontes (sem login, sem custo) devolve o catálogo de balcões e, no MCP instalado, o que já está configurado no ambiente dela, lido pelo NOME da variável (o valor nunca é lido nem devolvido). No remoto (claude.ai, ChatGPT) ele não olha nada: pergunte.
Ordem de preferência quando há mais de uma opção, pelo que custa DE VERDADE pra pessoa:
- O que ela já paga fixo (assinatura Sogni, Magnific com crédito parado, a própria placa): custo marginal zero.
- O balcão onde ela tem crédito pré-pago (Kie, fal, WaveSpeed, Krea, Replicate, OpenRouter): custo por peça, em dólar.
sapiens_video/sapiens_imageem Sinapse: o único que serve motor exclusivo da casa e o único com a régua de qualidade da casa por trás. Não é o último por ser pior: é o último por ser o mais caro por peça.
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 · +13 tokens per session 5529cc0841e5
- 26d ago First seen · 87 lines · 180 tokens per session scan A 1065ce252942
pontes is a skill published in the GitHub repository inhabitants/sapiens-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 193 tokens to every session and 3,591 once invoked, about $0.0008 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
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
dcc-blender-assembly-pitfalls
Read this BEFORE writing any Blender geometry code through MCP, whenever you are about to (1) create or size mesh primitives - bpy.ops.mesh.primitivecubeadd, primitivecylinderadd, primitiveuvsphereadd, primitiveconeadd - or set scale / dimensions on a part; (2) orient a part with rotationeuler or rotationquaternion…
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.
split-to-prs
Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.
quantum-algorithms
A routing workflow for choosing an open-source quantum-computing algorithm and loading the matching local workflow. Quantum computing uses circuits and quantum states to represent and process information.