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 Heapy/kortexnpx agentmods add plugins/heapy/kortex/marketplacegit clone --depth 1 https://github.com/Heapy/kortexGrade A, and why
kortex 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 yesterday.
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": "kortex",
"owner": {
"name": "Ruslan Ibrahimau",
"email": "[email protected]"
},
"metadata": {
"description": "Agent Skills for Kotlin development, task workflows, personal workflows, and Heapy packages",
"version": "1.12.0"
},
"plugins": [
{
"name": "kortex",
"source": "./plugins/kortex",
"description": "Kotlin Agent Skills — Kotlin Toolchain (Amper), Kotlin/JVM, Multiplatform, and more",
"version": "1.12.0",
"keywords": [
"kotlin",
"amper",
"toolchain",
"jvm",
"multiplatform",
"gradle"
],
"category": "languages"
},
{
"name": "kotlin-quality",
"source": "./plugins/kotlin-quality",
"description": "Kotlin test, architecture, and library ABI review agents — meaningful tests, clean core, effects at the boundary, no broken releases",
"version": "1.12.0",
"keywords": [
"kotlin",
"review",
"tests",
"architecture",
"solid",
"quality"
],
"category": "languages"
},
{
"name": "heapy",
"source": "./plugins/heapy",
"description": "Personal skills and Heapy package skills for komok, kinetica, and related workflows",
"version": "1.12.0",
"keywords": [
"heapy",
"heapy-packages",
"komok",
"kinetica",
"personal",
"issues"
],
"category": "productivity"
},
{
"name": "kotgent",
"source": "./plugins/kotgent",
"description": "Repository-aware task workflows using the kotgent CLI and git",
"version": "1.12.0",
"keywords": [
"kotgent",
"tasks",
"backlog",
"workflow",
"repository"
],
"category": "productivity"
}
]
}
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.
- yesterday First seen · 73 lines scan A 508b8aac927d
kortex is a plugin published in the GitHub repository Heapy/kortex (5 stars, last pushed 3d 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 2026-08-31.
Other plugins, from other repositories
cesiumjs-skills
Plugin marketplace listing 1 plugin: cesiumjs-skills.
cesiumjs-skills
Claude Code plugin for CesiumJS domain skills and browser-based iteration via Chrome DevTools.
respira-wordpress-skills
46 specialised WordPress skills covering page-builder migrations (12 paths including Divi to Gutenberg, Elementor to Bricks, WPBakery to Gutenberg), site audits (technical debt, mobile experience, WooCommerce health), content workflows (internal linking, content portability, SEO/AEO), and onboarding. Auto-activates…
data-analysis-ml-agent-skills
Evidence-first data analysis and ML skills for AI coding agents.
data-analysis-ml-agent-skills
Evidence-first AI agent skills for reliable data analysis, machine learning, and reproducible model validation.
bitwise
Bitwise Media Group skills and plugins for coding agents.