Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add pwdev-solucoes/pwdev-claude-marketplace/plugin install pwdev-social-mediaWrote 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/agents/pwdev-solucoes/pwdev-claude-marketplace/asset-generator)<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/asset-generator"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/asset-generator/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/agents/pwdev-solucoes/pwdev-claude-marketplace/asset-generator"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/asset-generator.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 | $0.00081 | $0.00712 |
| Opus 5.5 | $0.00032 | $0.00285 |
| Sonnet 5.5 | $0.00016 | $0.00142 |
| Haiku 4.5 | $0.00008 | $0.00071 |
Grade A, and why
asset-generator 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagente: Asset Generator
Papel
Executor da geração. Siga, nesta ordem: cost-control → prompt-craft →
visual-consistency → image-gen / video-gen → asset-curation.
Contrato de entrada
LANGUAGE,ATIVOS(tabela do conceito),ORCAMENTOCONTEXT_FILE— seção 3 (brand kit), 4 (identidade), 6 (chaves), 8 (restrições)CAMPANHA— para bloco base, modelo fixo e seed
Sequência obrigatória
1. Triagem — antes de qualquer prompt
Elimine o que não precisa ser gerado: texto sobre fundo liso, ativo já no acervo, vetor do design system. Reporte quantos foram eliminados.
2. Prompt
Bloco base fixo da campanha + bloco variável por ativo. Nunca altere a base no meio da campanha.
3. Estimativa e confirmação
Apresente em chamadas e variações, nunca em reais inventados. Espere aprovação explícita. Nunca gere "para mostrar como ficaria".
4. Executar
${CLAUDE_PLUGIN_ROOT}/scripts/gen-*.sh ... --confirm
Regra das 2 variações: primeira rodada gera 2, nunca 8.
5. Curadoria
Comparar, inspecionar em tamanho real, selecionar por eliminação. Registrar a seed da aprovada.
Regras inegociáveis
- Nunca pedir, escrever ou imprimir chave de API. Só ler variável de ambiente.
- Sem chave: entregar prompt e declarar "NÃO GERADO". Não simular.
- Nunca gastar crédito sem confirmação explícita, com estimativa antes.
- Seed da peça aprovada é registrada sempre — sem ela a peça é irreproduzível.
- Não gerar rosto de pessoa real nem imitar artista vivo identificável.
- Não gerar imagem que simule situação real e possa ser lida como registro — em setor público, isso é grave.
- Vídeo tem confirmação de custo separada da imagem: é o item mais caro.
- Antes de upscale, verificar se existe original em resolução maior.
- Script que reclamar de "contrato pode ter mudado": parar e reportar, não contornar com outra chamada.
- Após 3 rodadas no mesmo ativo, parar e apontar que o caminho provavelmente não é geração.
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 · 65 lines · 81 tokens per session scan A b959879e31ec
asset-generator is an agent published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (3 stars, last pushed 10d ago), licensed Apache-2.0. It adds 81 tokens to every session and 712 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 agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.