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 duyet/codex-claude-pluginsnpx agentmods add plugins/duyet/codex-claude-plugins/unsloth-traininggit clone --depth 1 https://github.com/duyet/codex-claude-pluginsWrote 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/duyet/codex-claude-plugins/unsloth-training)<a href="https://agentmods.dev/plugins/duyet/codex-claude-plugins/unsloth-training"><img src="https://agentmods.dev/badge/plugins/duyet/codex-claude-plugins/unsloth-training.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
unsloth-training 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 First seen · 11 lines scan A f5c63c63fd71
unsloth-training is a plugin published in the GitHub repository duyet/codex-claude-plugins (14 stars, last pushed today), with no licence file. 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 2026-09-03.
Other plugins, from other repositories
apple-foundation-models
Expert Apple FoundationModels guidance: SystemLanguageModel, LanguageModelSession, Generable, Tool, adapters, streaming, and GenerationError handling for iOS 26+.
swift
Swift development tools: automatic formatting with swift-format, and SwiftData expert guidance for @Model, @Query, @Relationship, migrations, concurrency, and architecture auditing.
apple-dev
Modern SwiftUI doctrine plus 7 recipes for Apple-platform development: no-ViewModel patterns, modular SwiftPM, Foundation Models on-device LLM, AppRouter navigation, iOS 26 Liquid Glass, encrypted push proxy, XcodeBuildMCP build verification, ObservableObject-to-Observable refactor.
ios-ai-ml-skills
AI and machine learning: Foundation Models, Core ML, Vision, NaturalLanguage, Speech Recognition.
apple-toolchain-mcp
LLVM compile, link, and inspect tools for Apple platforms (macOS, iOS). v1.0.1 MCP server published to Smithery, Glama, and MCP.so. Enables AI agents to perform native Apple toolchain operations with revenue model ($0.001 ETH per compile, 5% treasury to Genesis Conductor). Bridges seamlessly to OpenClaw skills via mcp.
ios-ai-ml-skills
AI and machine learning: Foundation Models, Core ML, Vision, NaturalLanguage, Speech Recognition.