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.
git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/plugins/pwdev-solucoes/pwdev-claude-marketplace/pwdev-social-media)<a href="https://agentmods.dev/plugins/pwdev-solucoes/pwdev-claude-marketplace/pwdev-social-media"><img src="https://agentmods.dev/badge/plugins/pwdev-solucoes/pwdev-claude-marketplace/pwdev-social-media/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/plugins/pwdev-solucoes/pwdev-claude-marketplace/pwdev-social-media"><img src="https://agentmods.dev/badge/plugins/pwdev-solucoes/pwdev-claude-marketplace/pwdev-social-media.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pwdev-social-media 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 6d 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.
What it actually says
{
"name": "pwdev-social-media",
"displayName": "PWDEV Social Media — Geração de Criativos por IA",
"version": "2.0.1",
"description": "Produção de criativos para redes sociais com orquestração de APIs de geração no centro — Ideogram, Leonardo, Flux, Runway e Freepik/Magnific via wrappers com trava de gasto; triagem de custo, engenharia de prompt, consistência visual e curadoria de variações. Figma como camada opcional de composição. 19 skills, 4 subagentes, revisão de acessibilidade obrigatória.",
"author": {
"name": "Paulo Soares",
"url": "https://github.com/soarescbm"
},
"homepage": "https://github.com/pwdev-solucoes/pwdev-claude-marketplace",
"repository": "https://github.com/pwdev-solucoes/pwdev-claude-marketplace",
"license": "Apache-2.0",
"keywords": [
"claude-code",
"claude-plugin",
"social-media",
"image-generation",
"ideogram",
"flux",
"runway",
"figma",
"creative-production",
"accessibility",
"pt-br"
],
"mcpServers": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 19 skills, 5 commands, 4 agents travel with it, and installing the plugin installs all of them — 2,012 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill creative-concept A 88 tokens
- Skill image-gen A 104 tokens
- Skill creative-review A 90 tokens
- Skill figma-pipeline A 92 tokens
- Skill prompt-craft A 89 tokens
- Skill video-gen A 100 tokens
- Skill visual-consistency A 84 tokens
- Skill alt-text A 77 tokens
- Skill asset-curation A 82 tokens
- Skill asset-upscale A 80 tokens
- Skill brand-kit A 96 tokens
- Skill carousel-builder A 84 tokens
- Skill cost-control A 76 tokens
- Skill export-handoff A 81 tokens
- Skill post-visual A 85 tokens
- Skill story-reels A 90 tokens
- Skill vault-sync A 82 tokens
- Skill social-context A 95 tokens
- Skill format-specs A 75 tokens
- Command criar A 30 tokens
- Command gerar A 19 tokens
- Command carrossel A 21 tokens
- Command video A 19 tokens
- Command exportar A 17 tokens
- Agent figma-builder A 59 tokens
- Agent asset-generator A 81 tokens
- Agent creative-reviewer A 58 tokens
- Agent art-director A 58 tokens
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.
- 6d ago First seen · 28 lines scan A b8fcb47597de
pwdev-social-media is a plugin published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
manim-skills
Manim (math animation) skills for AI coding agents — animate equations, plot functions, and render 3Blue1Brown-style explainers to MP4 with Manim Community Edition.
minli-skill
A collection of Claude Code skills, where Claude Code is an AI programming assistant. It includes a video-explanation workflow and a template for formatting WeChat Official Accounts posts.
motion-design-skills
Motion design fundamentals, engines, and brand elements as installable skills for AI coding agents — timing, typography, color, composition, After Effects, Remotion, logos, and backgrounds.
twelvelabs
TwelveLabs video AI integration. Index, search, and analyze videos using TwelveLabs' multimodal AI platform.
write-a-readme
Turn codebases into accurate, on-brand READMEs with editable SVG banners.
skind-skills
Investment research and educational video creation.