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 Blazity/atlasnpx agentmods add plugins/blazity/atlas/marketplacegit clone --depth 1 https://github.com/Blazity/atlasGrade A, and why
blazity marketplace 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 2d 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
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "blazity",
"description": "Blazity Atlas plugins for governed AI engineering workflows.",
"owner": {
"name": "Blazity",
"url": "https://github.com/Blazity"
},
"plugins": [
{
"name": "nextjs-migration-plugin",
"description": "Guided component-first migrations from public websites to production-ready Next.js App Router projects.",
"author": {
"name": "Blazity"
},
"category": "development",
"source": {
"source": "github",
"repo": "Blazity/nextjs-migration-plugin",
"ref": "main"
},
"homepage": "https://github.com/Blazity/nextjs-migration-plugin"
},
{
"name": "atlas",
"description": "Set up and maintain your repo's AI context — AGENTS.md, memory, vocabulary, ADRs — and run reviews that leave recorded verdicts. One shared workspace for Claude Code, Cursor, and Codex.",
"author": {
"name": "Blazity"
},
"category": "development",
"source": {
"source": "github",
"repo": "Blazity/atlas",
"ref": "main"
},
"homepage": "https://github.com/Blazity/atlas"
}
]
}
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.
- 2d ago First seen · 40 lines scan A 0f6463919456
blazity marketplace is a plugin published in the GitHub repository Blazity/atlas (24 stars, last pushed 1mo 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 2026-08-30.
Other plugins, from other repositories
memory-kit
Persistent memory for coding agents: a hot cache injected every session and held under three size caps, per-session handoffs, and agent-audited promotion into knowledge articles and rules. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second opinion, agent QA and a system…
aiboarding
Keep canonical AGENTS.md onboarding current for AI coding agents, with drift tracking, compression, and auditing.
agent-rules-skill
Generate and maintain AGENTS.md, copilot-instructions.md, and other agent rule files.
andrej-karpathy-skills
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
agents-md
Automatically loads AGENTS.md files alongside CLAUDE.md for cross-tool compatibility.
claude-md-kit
Scaffold, audit and migrate CLAUDE.md files from inside Claude Code: /claude-md-new builds one from battle-tested templates using your repo's real commands; /claude-md-audit grades an existing one and returns worst-first fixes; /claude-md-migrate rewrites a bloated file into the lean verified style.