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 szarkans/multinpx agentmods add plugins/szarkans/multi/marketplacegit clone --depth 1 https://github.com/szarkans/multiGrade A, and why
szkills 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 2d 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": "szkills",
"owner": {
"name": "szarkans",
"url": "https://github.com/szarkans"
},
"description": "my awesome skills",
"plugins": [
{
"name": "multi",
"source": "./",
"description": "Several models on the same question at once — Claude sub-agents, OpenAI Codex and a cheap third via OpenCode. Review code, check whether the work is actually finished, brainstorm wide with a different model per cognitive frame, or just ask all of them something.",
"version": "2.7.0",
"author": {
"name": "szarkans",
"url": "https://github.com/szarkans"
},
"homepage": "https://github.com/szarkans/multi",
"repository": "https://github.com/szarkans/multi",
"license": "MIT",
"keywords": [
"code-review",
"codex",
"opencode",
"multi-model",
"consensus",
"review",
"verification"
],
"category": "productivity"
}
]
}
What ships with it
1 file beside marketplace.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.
- 2d ago First seen · 34 lines scan A 74b3e10805a4
szkills is a plugin published in the GitHub repository szarkans/multi (8 stars, last pushed 2d 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.
Other plugins, from other repositories
sound
Code taste as installable rules. Probe a repo's stack, select only the rules its code shows a surface for (evidence-cited per rule), confirm, and scaffold a browsable .claude/sound/ rule map (surfaced by the sound:prime skill). Installed rules are user-owned; re-runs reconcile.
neatcontext
Save Claude Code work as reusable, domain-aware context.
neatcontext
Save Claude Code work as reusable, domain-aware context.
rails-consultant
Plugin marketplace listing 1 plugin: rails-consultant.
rails-consultant
A collection of skills for Rails development and consulting, with an emphasis on learning, communication, and client success.
kortex
Kotlin Agent Skills — Kotlin Toolchain (Amper), Kotlin/JVM, Multiplatform, and more.