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 sanity-io/agent-toolkitnpx agentmods add plugins/sanity-io/agent-toolkit/marketplacegit clone --depth 1 https://github.com/sanity-io/agent-toolkitGrade A, and why
sanity-agent-toolkit 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agent-toolkit — 91% identical, 47 lines differ
What it actually says
{
"name": "sanity-agent-toolkit",
"owner": {
"name": "Sanity",
"email": "[email protected]",
"url": "https://www.sanity.io"
},
"metadata": {
"description": "Sanity plugin for Claude Code with MCP server, agent skills, and agent rules.",
"version": "1.0.0"
},
"plugins": [
{
"name": "sanity",
"source": "./",
"description": "Sanity plugin for Claude Code with MCP server, agent skills, agent rules, and slash commands.",
"version": "1.0.0",
"homepage": "https://github.com/sanity-io/agent-toolkit",
"repository": "https://github.com/sanity-io/agent-toolkit",
"license": "MIT",
"keywords": [
"sanity",
"cms",
"content-lake",
"groq",
"content",
"structured-content",
"visual-editing"
],
"author": {
"name": "Sanity",
"email": "[email protected]",
"url": "https://www.sanity.io"
},
"category": "cms",
"tags": ["sanity", "cms", "groq", "structured-content", "visual-editing"]
}
]
}
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 c46c584a9eab
sanity-agent-toolkit is a plugin published in the GitHub repository sanity-io/agent-toolkit (180 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 2026-08-30.
Other plugins, from other repositories
taskmaster
A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.
astra
AST-powered codebase memory for AI agents. Cuts token usage 93% by injecting only relevant code context via knowledge graph + PageRank.
guide
Plugin marketplace listing 1 plugin: engineering-standards.
jeremydev87
Plugin marketplace listing 1 plugin: codingbuddy.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
nextjs
Official Claude Code plugin marketplace for Next.js, serving the skills that ship in the vercel/next.js repository.