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 bittlebitsai/bittlebits-pluginnpx agentmods add plugins/bittlebitsai/bittlebits-plugin/marketplacegit clone --depth 1 https://github.com/bittlebitsai/bittlebits-pluginGrade A, and why
bittlebits 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 yesterday.
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": "bittlebits",
"owner": {
"name": "BittleBits.ai",
"email": "[email protected]",
"url": "https://bittlebits.ai"
},
"metadata": {
"description": "BittleBits MCP plugins — GEO scoring and AI-content rewrite tools for Claude, Cursor, and any MCP client.",
"version": "1.0.0"
},
"plugins": [
{
"name": "bittlebits-mcp-plugin",
"source": "./",
"description": "Connect Claude, Cursor, and any MCP client to BittleBits GEO scores and rewrite suggestions over a remote OAuth MCP server (Streamable HTTP).",
"homepage": "https://bittlebits.ai/docs/mcp",
"license": "MIT",
"keywords": [
"mcp",
"model-context-protocol",
"claude",
"cursor",
"geo",
"seo",
"ai-seo",
"bittlebits"
]
}
]
}
What ships with it
1 file beside marketplace.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.
- yesterday First seen · 32 lines scan A f3fada6549d8
bittlebits is a plugin published in the GitHub repository bittlebitsai/bittlebits-plugin (0 stars, last pushed 3mo 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
claude-rank
Plugin marketplace listing 1 plugin: claude-rank.
claude-rank
Claude Code plugin that tells you why your site won't get cited by AI — and fixes the discoverability files automatically.
semantic-seo-suite
Plugin marketplace listing 1 plugin: semantic-seo-suite.
semantic-seo-suite
Grounded semantic SEO, GEO & off-page as Claude Code skills — topical maps, briefs, fabrication-guarded drafts, schema, audits, GEO, backlinks, distribution.
aaron
Plugin marketplace listing 1 plugin: aaron-marketing.
fire-your-seo-agency
Fire your SEO agency — a Claude Code skill that audits and implements SEO·AEO·GEO·LLMO·NEO(Naver) itself: crawler-eye audit, intent landing pages, llms.txt, structured data, Naver AI Briefing, and a measurement loop.