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 andregusman-raiz/a-gusman-claude --skill gerar-imagemgit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claudeWrote 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/andregusman-raiz/a-gusman-claude/gerar-imagem)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/gerar-imagem"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/gerar-imagem/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/andregusman-raiz/a-gusman-claude/gerar-imagem"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/gerar-imagem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00079 | $0.00933 |
| Opus 5.5 | $0.00032 | $0.00373 |
| Sonnet 5.5 | $0.00016 | $0.00187 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
gerar-imagem 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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gerar Imagem — Nano Banana (Gemini) / OpenAI (gpt-image-1)
Dois providers com a mesma interface; chaves lidas em runtime — NUNCA ecoar a chave.
| Provider | Script | Chave (runtime) | Status |
|---|---|---|---|
OpenAI gpt-image-1 |
~/Claude/.claude/scripts/openai-image.sh |
OPENAI_API_KEY env → ~/.claude/state/openai-image.env → ~/Claude/.env |
usar como default |
| Nano Banana (Gemini) | ~/Claude/.claude/scripts/nano-banana.sh |
NANO_BANANA_API_KEY env → ~/.claude/state/nano-banana.env → ~/Claude/.env |
BLOQUEADO até billing no projeto Google (free tier = 0 p/ imagem) |
Uso
# OpenAI — geração simples / paisagem / edição
bash ~/Claude/.claude/scripts/openai-image.sh -p "prompt detalhado em inglês" -o saida.png
bash ~/Claude/.claude/scripts/openai-image.sh -p "..." -s 1536x1024 -q high -o hero.png
bash ~/Claude/.claude/scripts/openai-image.sh -p "change background to teal" -i original.png -o editada.png
# Nano Banana (quando billing ativar) — aspect ratio + modelo pro
bash ~/Claude/.claude/scripts/nano-banana.sh -p "..." -a 16:9 -m pro -o hero.png
bash ~/Claude/.claude/scripts/nano-banana.sh -p "change background to teal" -i original.png -o editada.png
Regras
- Prompt em inglês, descritivo e narrativo (cena, estilo, iluminação, composição) — Nano Banana responde melhor a descrição de cena do que a lista de keywords. Incluir estilo explícito ("flat vector illustration", "photorealistic", "3D render", "isometric").
- Modelo:
flash(default, ~US$0,04/img) para tudo;-m prosó quando precisar de texto renderizado dentro da imagem ou fidelidade máxima (mais caro). - Destino: asset de projeto →
<projeto>/public/ou<projeto>/assets/; exploração/rascunho → scratchpad da sessão. Nome descritivo, nuncaimage.png. - Verificação obrigatória (DoD): após gerar,
Readno PNG para conferir visualmente se atende ao pedido. Se não atende, refinar o prompt e regenerar (máx 3 iterações, depois reportar gap). - Identidade Raiz: se o asset for para projeto Raiz, usar tokens do design system no prompt (laranja #F7941D, teal #5BB5A2, estilo clean/minimal, IBM Plex como referência tipográfica).
- Edição: para variação/retoque de imagem existente, SEMPRE passar a original via
-iem vez de tentar regenerar do zero — preserva composição e identidade. - Aspect ratios suportados: 1:1 (default), 16:9, 9:16, 4:3, 3:4, 21:9, 2:3, 3:2, 4:5, 5:4.
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.
- 1mo ago First seen · 50 lines · 79 tokens per session scan A 2b6489d29a30
gerar-imagem is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (18 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 933 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 2026-09-03.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.