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/flagos-ai/skillsWrote 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/flagos-ai/skills/skills)<a href="https://agentmods.dev/plugins/flagos-ai/skills/skills"><img src="https://agentmods.dev/badge/plugins/flagos-ai/skills/skills/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/flagos-ai/skills/skills"><img src="https://agentmods.dev/badge/plugins/flagos-ai/skills/skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
flagos-skills 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 1mo 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": "flagos-skills",
"description": "Agent skills for the FlagOS multi-chip AI inference platform. Includes kernel generation and optimization, model migration, environment verification, vendor onboarding, and more.",
"version": "1.1.0",
"author": {
"name": "FlagOS Contributors"
},
"homepage": "https://github.com/flagos-ai/skills",
"repository": "https://github.com/flagos-ai/skills",
"license": "Apache-2.0",
"keywords": [
"flagos",
"multi-chip",
"vllm",
"model-migration",
"kernel-generation",
"triton",
"pytorch",
"inference",
"gpu",
"npu",
"deployment"
]
}
What it installs
The manifest is a name and a version. 13 skills travel with it, and installing the plugin installs all of them — 1,268 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill flaggems-pr-submit-flagos A 100 tokens
- Skill skill-creator-flagos A 135 tokens
- Skill flaggems-pr-review-flagos A 119 tokens
- Skill flagrelease-entrance-flagos A 93 tokens
- Skill gpu-container-setup-flagos A 71 tokens
- Skill install-stack-flagos A 78 tokens
- Skill kernelgen-flagos A 117 tokens
- Skill model-migrate-flagos A 187 tokens
- Skill vllm-plugin-fl-setup-flagos A 117 tokens
- Skill model-verify-flagos A 61 tokens
- Skill tle-developer-flagos A 89 tokens
- Skill template-skill A 36 tokens
- Skill perf-test-flagos C 65 tokens
What ships with it
1 file beside plugin.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.
- 1mo ago First seen · 25 lines scan A af25acf7bc21
flagos-skills is a plugin published in the GitHub repository flagos-ai/skills (22 stars, last pushed 3mo 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
dgx-spark-ops
NVIDIA DGX Spark (GB10 Grace Blackwell) environment operations: aarch64/CUDA-13 stack setup, training gotcha preflights, and unified-memory/thermal management for local ML workloads.
nvidia-skills
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered workflows.
coreai-skills
Skills for authoring, exporting, compiling, and running PyTorch models on Apple silicon via Core AI.
amd-skills
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom, and analyze GPU kernel and PyTorch trace performance.
intel-gpu-ai-skills
Agent Skills for running, benchmarking, profiling, and fixing arbitrary Hugging Face safetensors models on Intel GPUs. Container-first, upstream-only, Battlemage / Arc / Arc Pro / Data Center GPU Max.
awesome-ascend-skills marketplace
A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed AI Agent Skills. Includes npu-smi device management, HCCL performance testing, and ATC model conversion.