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/mrlm-xyz/demo-claude-marketplaceWrote 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/mrlm-xyz/demo-claude-marketplace/data-toolkit)<a href="https://agentmods.dev/plugins/mrlm-xyz/demo-claude-marketplace/data-toolkit"><img src="https://agentmods.dev/badge/plugins/mrlm-xyz/demo-claude-marketplace/data-toolkit/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/mrlm-xyz/demo-claude-marketplace/data-toolkit"><img src="https://agentmods.dev/badge/plugins/mrlm-xyz/demo-claude-marketplace/data-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
data-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 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": "data-toolkit",
"description": "Adds data engineering agents, commands, and skills for ETL pipeline development.",
"version": "0.1.0"
}
What it installs
The manifest is a name and a version. 2 skills, 2 commands, 2 agents travel with it, and installing the plugin installs all of them — 128 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 · 6 lines scan A a7b2cc619514
data-toolkit is a plugin published in the GitHub repository mrlm-xyz/demo-claude-marketplace (35 stars, last pushed 2mo ago), licensed Apache-2.0. 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.
data-toolkit compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| data-toolkitmrlm-xyz/demo-claude-marketplace | Plugin | 35 | 2mo ago | Apache-2.0 | A | — | Claude Code |
| clip-aware-embeddingscuriositech/some_claude_skills | Plugin | 263 | 4d ago | MIT | A | — | Claude Code |
| tao-skill-bankNVIDIA-TAO/tao-skill-bank | Plugin | 100 | today | Apache-2.0 | A | — | Claude Code |
| classifiercardmagic/classifier | Plugin | 741 | 2d ago | none | A | — | Claude Code |
| databricksdatabricks/databricks-agent-skills | Plugin | 392 | today | none | A | — | Claude Code, Cursor |
| twelvelabstwelvelabs-io/twelve-labs-claude-code-plugin | Plugin | 26 | 1mo ago | MIT | A | — | Claude Code |
| sql-database-pipelinedlt-hub/dlthub-ai-harness | Plugin | 65 | 4d ago | none | A | — | Claude Code |