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 videogit 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/video)<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/video"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/video/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/video"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/video.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 | $0.00049 | $0.04104 |
| Opus 5.5 | $0.00020 | $0.01642 |
| Sonnet 5.5 | $0.00010 | $0.00821 |
| Haiku 4.5 | $0.00005 | $0.00410 |
Grade A, and why
video 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vídeo: escolher modelo sem queimar Sinapses
Antes de tudo
action=create EXIGE model. Sem model, falha de cara. Vídeo é o mais caro: confirme com a pessoa antes de disparar.
action=models (sem custo, sem login) lista os modelos ativos com durações, resoluções, disponibilidade e a FAIXA de preço: o padrão, o piso e o teto, cada um dizendo em qual configuração acontece. Motor de preço-por-segundo não tem "um preço": o mesmo modelo custa 3x mais em 1080p e 30s do que em 720p e 5s.
Dois campos do payload evitam garimpo na lista. bestFor diz pra que o motor serve (audio = som nativo, fala = lip-sync, referencia = aceita referência de quem aparece, movimento = precisa de vídeo-guia, longo = passa dos 15s): filtre por aqui antes de comparar preço. family + variant dizem quem é o mesmo motor em geração ou tier diferente: as quatro linhas de Seedance (2.0, 2.0 Fast, 2.0 Mini, 2.5) são UM motor, não quatro. Escolha a família pelo trabalho, depois a variante pela conta.
action=price (sem custo, sem login) cota a configuração EXATA antes de rodar: passe model, durationSec, resolution e audio e receba o número que vai ser debitado, calculado pela mesma função que cobra. Ela também avisa quando o motor não aceita o que você pediu e vai cobrar outra coisa (clamped), o que acontece quando a duração não existe no enum ou a resolução cai num tier diferente.
Use price sempre que a pessoa perguntar quanto custa, e ANTES de qualquer create que não seja o default. Dizer o piso como se fosse o preço final é o jeito mais rápido de queimar a confiança dela: a cobrança vem maior e a culpa é sua.
Iterar barato, fechar caro
Os três Seedance 2.0 têm o MESMO repertório (referência, frame inicial e final, vídeo de movimento, áudio nativo):
| Modelo | Custo | Teto |
|---|---|---|
sapiens-video-seedance-2-mini |
metade do padrão | 720p |
sapiens-video-seedance-2-fast |
20% menos | 720p |
sapiens-video-seedance |
padrão | 1080p |
Itere enquadramento e prompt no Mini, feche no padrão quando o take estiver certo. Economiza Sinapses da pessoa sem trocar de fluxo. Pedir 1080p nos dois de cima entrega e cobra 720p.
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 · +29 lines 535424a98d63
- 26d ago First seen · 101 lines · 49 tokens per session scan A 0d1b129342c6
video is a skill published in the GitHub repository inhabitants/sapiens-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 4,104 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
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.