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.
git clone --depth 1 https://github.com/worldcoin/agentkitWrote 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/worldcoin/agentkit/agentkit)<a href="https://agentmods.dev/plugins/worldcoin/agentkit/agentkit"><img src="https://agentmods.dev/badge/plugins/worldcoin/agentkit/agentkit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/worldcoin/agentkit/agentkit"><img src="https://agentmods.dev/badge/plugins/worldcoin/agentkit/agentkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agentkit 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 2mo 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": "agentkit",
"version": "0.1.6",
"description": "Skills for registering and using AgentKit — prove your agent is backed by a real human to get free or discounted access to x402 endpoints.",
"author": {
"name": "Worldcoin"
},
"repository": "https://github.com/worldcoin/agentkit",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 109 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 2mo ago First seen · 11 lines scan A cc4ab9652ccd
agentkit is a plugin published in the GitHub repository worldcoin/agentkit (25 stars, last pushed 17d 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.
agentkit compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentkitworldcoin/agentkit | Plugin | 25 | 17d ago | MIT | A | — | Claude Code |
| sp-globalcursor/plugins | Plugin | 15k | yesterday | none | A | — | Cursor |
| investorferdousbhai/investor-agent | Plugin | 348 | 28d ago | MIT | A | — | Claude Code |
| shinkokukazukinagata/shinkoku | Plugin | 367 | 1mo ago | MIT | A | — | Claude Code |
| secedgar-mcp-servercyanheads/secedgar-mcp-server | Plugin | 11 | 2d ago | Apache-2.0 | A | — | Claude Code |
| bitbank-lab-mcpbitbankinc/bitbank-lab-mcp | Plugin | 5 | yesterday | MIT | A | — | Gemini CLI |
| datarails-financeosDatarails/dr-claude-code-plugins-re | Plugin | 3 | 12d ago | MIT | A | — | Claude Code |