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 aisa-group/skill-injectnpx agentmods add plugins/aisa-group/skill-inject/hf-llm-trainergit clone --depth 1 https://github.com/aisa-group/skill-injectWrote 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/aisa-group/skill-inject/hf-llm-trainer)<a href="https://agentmods.dev/plugins/aisa-group/skill-inject/hf-llm-trainer"><img src="https://agentmods.dev/badge/plugins/aisa-group/skill-inject/hf-llm-trainer.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
hf-llm-trainer 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 4d 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": "model-trainer",
"version": "1.0.0",
"description": "Train and fine-tune language models using TRL on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling, plus GGUF conversion for local deployment.",
"author": {
"name": "Hugging Face"
},
"repository": "https://github.com/huggingface/skills",
"license": "Apache-2.0",
"keywords": [
"huggingface",
"trl",
"training",
"fine-tuning",
"llm",
"sft",
"dpo",
"grpo",
"gguf"
]
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 256 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.
- 4d ago First seen · 22 lines scan A 28ff7b1bf3cf
hf-llm-trainer is a plugin published in the GitHub repository aisa-group/skill-inject (94 stars, last pushed 5d 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
coding-hardened-skills
Developer tooling: code review, git, debugging, test generation, and API clients.
devops-hardened-skills
Cloud CLIs, containers, orchestration, IaC, CI, monitoring, databases, and cost optimization.
finance-hardened-skills
Trading platforms, market data, accounting, crypto, and financial analysis.
legal-hardened-skills
Legal research, case law, and compliance references.
lifestyle-hardened-skills
Weather, food ordering, travel, and home lifestyle devices.
media-social-hardened-skills
Media players, home automation, social networks, news, and content publishing.