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.
/plugin marketplace add AntonioBlago/claude-code-seo-starternpx agentmods add plugins/antonioblago/claude-code-seo-starter/claude-code-seo-startergit clone --depth 1 https://github.com/AntonioBlago/claude-code-seo-starterWrote 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/antonioblago/claude-code-seo-starter/claude-code-seo-starter)<a href="https://agentmods.dev/plugins/antonioblago/claude-code-seo-starter/claude-code-seo-starter"><img src="https://agentmods.dev/badge/plugins/antonioblago/claude-code-seo-starter/claude-code-seo-starter.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
seo-starter 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.
What it actually says
{
"name": "seo-starter",
"displayName": "SEO Agency & Freelancer Starter",
"version": "0.1.0",
"description": "Wire up the Visibly AI MCP and run the full SEO client workflow in Claude Code: status-quo, potential analysis, offer, and a CI-compliant PDF. Intent-aware CTR model from the Keyword Study 2026.",
"author": {
"name": "Antonio Blago",
"email": "[email protected]",
"url": "https://antonioblago.de"
},
"homepage": "https://github.com/AntonioBlago/claude-code-seo-starter",
"repository": "https://github.com/AntonioBlago/claude-code-seo-starter",
"license": "MIT",
"keywords": ["seo", "mcp", "visibly-ai", "agency", "freelancer", "gsc", "ctr"],
"commands": "./.claude/commands",
"skills": "./.claude/skills",
"hooks": "./.claude/hooks/hooks.json",
"mcpServers": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 4 skills, 4 commands, 1 hook, 2 MCP servers travel with it, and installing the plugin installs all of them — 334 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill visibly-seo-potential A 83 tokens
- Skill visibly-seo-status-quo A 72 tokens
- Skill visibly-seo-offer A 65 tokens
- Skill visibly-seo-pdf-build A 60 tokens
- Command visibly-seo-potential A 14 tokens
- Command visibly-seo-status-quo A 19 tokens
- Command visibly-seo-pdf-build A 10 tokens
- Command visibly-seo-offer A 11 tokens
- Hook UserPromptSubmit A not measured
- MCP server visibly-ai A not measured
- MCP server visiblyai A not measured
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 20 lines scan A 545976215861
seo-starter is a plugin published in the GitHub repository AntonioBlago/claude-code-seo-starter (2 stars, last pushed 2mo ago), licensed MIT. 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 2026-08-31.
Other plugins, from other repositories
dataforseo-brain
Source-cited Obsidian brain for the DataForSEO v3 API: 12 modules, 200+ endpoints, the task/live execution model, and per-call costs.
claude-wp-builder
WordPress site-building methodology: demo HTML → custom theme with ACF/SCF, bilingual support, section-by-section building.
youtube-agent-matrix
A complete YouTube channel operating system for Claude Code. Fourteen specialized subagents covering channel strategy, health audits, competitor intelligence, research, ideation, content calendars, hooks and retention-engineered scripts, thumbnails, SEO, upload metadata, Shorts, cross-platform repurposing…
studiomeyer-crew
13 expert agent personas for Claude Code — CEO, CFO, CMO, CTO, PM, Analyst, Creative Director and Support Lead plus 5 specialists. Zero extra API cost, runs inside your Claude subscription. Includes 3 multi-persona workflows (strategy-review, content-pipeline, product-launch). Free.
studiomeyer-geo
Generative Engine Optimization for Claude Code. 30 tools measuring AI visibility across ChatGPT, Gemini, Perplexity, Claude, Grok, DeepSeek, Meta AI, and Copilot. Discovery stack audits, schema generator, citation analysis, async job/poll checks. Most tools work without any LLM API key. Magic Link authentication. Free.
studiomeyer-memory
Hosted AI memory with 56 tools (incl. interactive 3D knowledge graph visualization). Knowledge Graph, semantic search, contradiction detection, multi-agent namespaces, import from ChatGPT/Claude/Gemini/Copilot/Perplexity. Magic Link authentication. EU Frankfurt hosting. Free tier available.