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 Smolevich/pet-project-atlasnpx agentmods add plugins/smolevich/pet-project-atlas/plugingit clone --depth 1 https://github.com/Smolevich/pet-project-atlasGrade A, and why
atlas 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "atlas",
"description": "Route a pet project through search, AI search, content, distribution and analytics.",
"version": "0.1.0",
"author": {
"name": "Smolevich"
},
"homepage": "https://atlas.smolevich.com",
"repository": "https://github.com/Smolevich/pet-project-atlas",
"license": "MIT",
"keywords": ["seo", "geo", "indexing", "analytics", "content"]
}
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 · 14 lines scan A b57e70d5ef76
atlas is a plugin published in the GitHub repository Smolevich/pet-project-atlas (2 stars, last pushed 7d 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.
thl-open
Plugin marketplace listing 1 plugin: thl-open.
claude-rank
Claude Code plugin that tells you why your site won't get cited by AI — and fixes the discoverability files automatically.
thl-open
AI-visibility engineering, the open way — the THL GEO / AI-search audit skill suite (citability, AI-crawler access, llms.txt, schema, brand mentions, technical, content, reporting) plus the THL-original agent-readiness-scan, organised around the THL GEO Method.
sorank
Plugin marketplace listing 1 plugin: claude-seo-geo.
claude-seo-geo
SEO + GEO skills for Claude Code: audit any site, diagnose a traffic drop, fix technical SEO, write content that ranks on Google and gets cited by ChatGPT, Perplexity and AI Overviews, build links and brand mentions, amplify on social, and track AI visibility without paid tools. Runs on your company's Obsidian…