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/datathings/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/datathings/marketplace/rocm)<a href="https://agentmods.dev/plugins/datathings/marketplace/rocm"><img src="https://agentmods.dev/badge/plugins/datathings/marketplace/rocm/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/datathings/marketplace/rocm"><img src="https://agentmods.dev/badge/plugins/datathings/marketplace/rocm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
rocm 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 3d 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": "rocm",
"version": "3.2.4",
"description": "AMD ROCm 7.2.4 GPU computing stack: HIP kernel development, rocBLAS/rocFFT/rocRAND/rocSOLVER compute libraries, profiling, and CUDA-to-HIP porting",
"author": {
"name": "Datathings",
"email": "[email protected]"
},
"license": "MIT",
"repository": "https://github.com/datathings/marketplace",
"keywords": ["c++", "rocm", "hip", "gpu", "amd", "hpc", "cuda-porting"],
"skills": "./skills/"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 120 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.
- 3d ago Changed 44b426c21492
- 7d ago Changed 3cfe0e4ca4d8
- 9d ago Changed f10ffafc2d96
- 14d ago Changed bde73a3d1306
- 16d ago Changed 3cb5e90193b7
- 17d ago Changed 1f7ef89ef50c
- 21d ago Changed f194a0a1755c
- 23d ago Changed fb733004e649
- 1mo ago Changed 768247c96e42
- 1mo ago First seen · 14 lines scan A ffb858de2ae7
rocm is a plugin published in the GitHub repository datathings/marketplace (11 stars, last pushed 3d 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.
Other plugins, from other repositories
embedded-workbench
A collection of coding agents and skills for embedded C and C++, the languages commonly used for firmware in microcontrollers and other dedicated devices. It covers FreeRTOS, Keil MDK, ARMCLANG, hard-fault troubleshooting, state machines, system architecture, and LVGL patterns.
drogon
Drogon C++ backend rules & skills: correct async code, avoiding callback / event-loop pitfalls. Works with Claude Code, ZCode, Codex, Cursor, VS Code (Copilot), Gemini CLI and any AGENTS.md-compatible agent.
unreal-engine
Unreal Engine 5 development: Gameplay Framework, Blueprint or C++, the Gameplay Ability System, Enhanced Input, replication, and Lumen and Nanite.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.