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/aomi-labs/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/aomi-labs/skills/aomi)<a href="https://agentmods.dev/plugins/aomi-labs/skills/aomi"><img src="https://agentmods.dev/badge/plugins/aomi-labs/skills/aomi/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/aomi-labs/skills/aomi"><img src="https://agentmods.dev/badge/plugins/aomi-labs/skills/aomi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
aomi 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 today.
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": "aomi",
"description": "Aomi for AI agents \u2014 drive the Aomi CLI from natural-language prompts (chat, simulate, sign on-chain transactions with account-abstraction-aware execution) and scaffold new Aomi apps from API specs. Bundle ships two skills: aomi-transact (run on-chain across 40+ DeFi/perps/CEX/social apps on EVM mainnets and L2s) and aomi-build (scaffold Rust SDK crates from OpenAPI/Swagger specs).",
"version": "0.13.0",
"author": {
"name": "Aomi Labs",
"url": "https://aomi.dev",
"email": "[email protected]"
},
"homepage": "https://aomi.dev",
"repository": "https://github.com/aomi-labs/skills",
"license": "MIT",
"keywords": [
"aomi",
"ai-agents",
"account-abstraction",
"intent",
"natural-language",
"transactions",
"simulation",
"evm",
"defi",
"cli",
"sdk",
"scaffold",
"openapi",
"rust",
"code-generation"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 210 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.
- today Changed 96291866d2cf
- 1mo ago First seen · 31 lines scan A 35836b3827fa
aomi is a plugin published in the GitHub repository aomi-labs/skills (8 stars, last pushed today), 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 2026-08-31.
Other plugins, from other repositories
full
Every materials-simulation domain skill.
simulation-workflow
All simulation workflow skills.
reproducible-campaigns
Plan, run, diagnose, and FAIR-package multi-run simulation campaigns across HPC.
verification-and-validation
Prove a result is trustworthy: stability, convergence, manufactured solutions, and pre/post-flight validation.
core-numerical
All core numerical skills.
hpc-deployment
All hpc deployment skills.