agentmods.dev

ai-toolkit

ai-toolkit is a plugin for Claude Code from Aznatkoiny/zAI-Skills. Its manifest loads nothing; the 6 skills, 4 commands, 2 agents it bundles cost 1,613 tokens per session together, scanned A, original, MIT.

A collection of guides for deep learning with Keras 3, reinforcement learning in Python and C++, prompt optimisation, x402 Web3 payments, and OpenClaw setup. Keras is a library for building and training neural-network models.

In plain words
What is it for?
Use it when building neural networks, computer-vision or language models, time-series or generative models, reinforcement-learning programs, optimised prompts, x402 payment flows, or OpenClaw setups.
Why use it?
It gives you practical guidance across several specialised AI and developer topics instead of requiring separate starting points for each one. It also covers Keras use with JAX, TensorFlow, and PyTorch backends.

Plugin for Claude Code

not rated 9 1mo ago A scan tokens not measured original MIT
View the source file Aznatkoiny/zAI-Skills
Install

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.

Claude Code
/plugin marketplace add Aznatkoiny/zAI-Skills
agentmods
npx agentmods add plugins/aznatkoiny/zai-skills/ai-toolkit
Clone the repo
git clone --depth 1 https://github.com/Aznatkoiny/zAI-Skills

Made for: Claude Code.

Wrote 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.

agentmods badge for ai-toolkit

README.md
[![agentmods](https://agentmods.dev/badge/plugins/aznatkoiny/zai-skills/ai-toolkit.svg)](https://agentmods.dev/plugins/aznatkoiny/zai-skills/ai-toolkit)
Your own site
<a href="https://agentmods.dev/plugins/aznatkoiny/zai-skills/ai-toolkit"><img src="https://agentmods.dev/badge/plugins/aznatkoiny/zai-skills/ai-toolkit.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 6 skills, 4 commands, 2 agents cost 1,613 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

ai-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 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.

AI-Toolkit/.claude-plugin/plugin.json · 24 lines

What it actually says

{
  "name": "ai-toolkit",
  "version": "2.4.0",
  "description": "Skills for Deep Learning (Keras 3), Reinforcement Learning (Python & C++), Claude Prompt Optimization, x402 Web3 Payments, and OpenClaw Setup.",
  "author": {
    "name": "Antony Zaki"
  },
  "homepage": "https://github.com/Aznatkoiny/zAI-Skills",
  "repository": "https://github.com/Aznatkoiny/zAI-Skills",
  "license": "MIT",
  "keywords": [
    "deep-learning",
    "reinforcement-learning",
    "prompt-engineering",
    "x402",
    "keras",
    "pytorch",
    "gymnasium",
    "web3",
    "machine-learning",
    "openclaw"
  ]
}
Contents

What it installs

The manifest is a name and a version. 6 skills, 4 commands, 2 agents travel with it, and installing the plugin installs all of them — 1,613 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

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.

  1. 4d ago First seen · 24 lines scan A d6239f8cdcd7

Subscribe to this mod's changes

ai-toolkit is a plugin published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo 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 2026-08-31.

Data and AIFinance and fintechWeb3 and blockchainai-toolsanthropicclaude-codeclaude-code-pluginconsultingdeep-learning
Related

Other plugins, from other repositories

crypto-trading-desk

Multi-agent cryptocurrency intelligence system with 7 specialized AI agents, 9 MCP servers (95 tools), cognitive learning, and self-evolving capabilities for comprehensive market analysis and paper trading.

hugoguerrap/crypto-claude-desk · not measured

credo

The mentor framework for Claude Code: a self-contained process layer with per-session modes, a work-item lifecycle with a hard Definition of Done, budget-aware autonomy, visual verification, and safety rules that travel into every subagent.

Marcel-Bich/marcel-bich-claude-marketplace · not measured

0xarchive

Agent-ready 0xArchive market data skill for coding-agent clients across Hyperliquid and Lighter.xyz, including Hyperliquid HIP-3 builder perps, HIP-4 outcome markets, and Hyperliquid Spot. REST and WebSocket support are route-specific; HIP-4 trades, L4 events, and settlements are live while HIP-4 L2 and OI use REST or.

0xArchiveIO/0xarchive-skill · not measured

yield-xyz-agentkit-moonpay

The MoonPay connector — sign and broadcast Yield.xyz transactions via MoonPay. Builds on the yield-xyz-agentkit base plugin.

stakekit/agentkit · not measured

yield-xyz-agentkit-privy

The Privy connector — sign and broadcast Yield.xyz transactions via Privy agentic wallets. Builds on the yield-xyz-agentkit base plugin.

stakekit/agentkit · not measured

yield-xyz-agentkit-robinhood

The Robinhood Chain connector — configure Robinhood Chain (mainnet, chain ID 4663) and act on Yield.xyz yields there. Builds on the yield-xyz-agentkit base plugin.

stakekit/agentkit · not measured