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 personagemgit 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/personagem)<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/personagem"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/personagem/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/personagem"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/personagem.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 | $0.00070 | $0.02640 |
| Opus 5.5 | $0.00028 | $0.01056 |
| Sonnet 5.5 | $0.00014 | $0.00528 |
| Haiku 4.5 | $0.00007 | $0.00264 |
Grade A, and why
personagem 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personagem no Midjourney (e trazer pra casa)
O que muda no Midjourney (e quase ninguém faz)
O veto vai no parâmetro, nunca no texto. Escrever "no 3D rendering" dentro do prompt faz o modelo ler as palavras 3D e rendering como parte da cena e desenhar justamente aquilo. O lugar do veto é --no 3d render, octane, plastic skin.
Prompt curto ganha. De 40 a 80 palavras. O Midjourney não é o Flux: prompt de 150 palavras dilui o peso de cada token e o miolo se perde. Se não coube, o conceito tem duas ideias brigando e vira dois prompts.
Ilustração 2D é o default. O modelo tem viés forte de render 3D e foto tratada, então personagem pedido no vazio volta parecendo cinemático de game. O que corrige é ancorar a mídia (crisp ink line art, expressive cel shading, anime key visual, high-end webtoon illustration), não empilhar adjetivo.
Os parâmetros que importam
--v 8.2explícito. É o default hoje, mas escrito o prompt dura mais que a versão.--ar: prancha larga3:2, grid de expressão1:1, key visual4:5.--s(stylize), 0 a 1000, default 100. Traço autoral vive entre 200 e 400; acima de 500 o modelo inventa e suja a linha.--sref <url ou código>com--sw: trava a ESTÉTICA entre imagens. É o que segura uma série.--oref <url>com--ow: trava a IDENTIDADE do personagem. Armadilha: no 8.x o job com--orefroda no motor V7 por baixo, então sai o personagem certo com o acabamento antigo. Quando o acabamento importa mais que o rosto, use--srefe descreva o personagem em texto.--niji 7pra anime e mangá puros (não existe Niji 8). Nunca no mesmo prompt que--v.- Ordem: texto, parâmetros,
--nopor último.
As cinco pranchas
Quando a pessoa pede variações, entregue cinco setups que mudam LAYOUT, não personagem: model sheet de corpo inteiro em fundo off-white; turnaround de três vistas; grid de 6 a 9 expressões; key visual de ação; estudo de silhueta com calls de figurino. Cinco vezes a mesma prancha com adjetivo trocado não é variação.
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 dc62323cab27
- 26d ago First seen · 82 lines · 70 tokens per session scan A 55516b6e6faf
personagem is a skill published in the GitHub repository inhabitants/sapiens-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 2,640 once invoked, about $0.0003 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
21st-ui
Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.
form-list-layout
Configure what a form and a list look like — sysuiform, sysuisection and sysuielement for forms; sysuilist, sysuilistelement and sysuirelatedlist for lists; sysfilter for saved filters. Views, why a field must exist in the dictionary first, and what snowcreatemenu really writes.
kernelcad-mcp
Load when kernelcad mcp is available and you need to inspect or edit a live model without re-running the full CLI on every change. The MCP server exposes dynamic introspection tools that operate on evaluated in-memory state.
kernelcad-kinematic
Use when verifying whether a moving assembly is buildable — sampled-pose collision sweeps across joint ranges, IK reachability for end-effector targets, mounting-hole fastener consistency, and static-load capacity on cantilever-shaped parts. Loads alongside kernelcad-authoring to gate design-time mechanism feasibility.
kernelcad-trace-from-image
Convert pixel-space features from a reference photo into normalized [0,1] waypoints, then into mm coordinates feedable to path().spline / path().nurbsSegment. Uses the tracefromimage MCP tool. Load when your blockout is in place and the next step is an organic-curve outline (upper contour, ergonomic handle, sneaker…
reticle-aesthetic
Build landing page sections, hero blocks, and marketing surfaces in the Reticle/Sigil engineering-instrument-grid aesthetic. Use when creating new landing sections, hero components, marketing pages, or when the user says "reticle", "hero", "landing page", "new section", "instrument panel", "grid cell", or wants to…