agentmods.dev

multi-dir-plugin

A plugin that declares more than one directory of skills for a coding agent to load.

In plain words
What is it for?
Use it as a plugin structure when skills are stored in both skills/ and experimental/ directories.
Why use it?
It lets a plugin organize its skills across separate folders, including a main set and an experimental set.

Plugin for Claude Code

146 7mo ago A scan tokens not measured original MIT
View the source file maxvaega/skillkit
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 maxvaega/skillkit
agentmods
npx agentmods add plugins/maxvaega/skillkit/multi-dir-plugin
Clone the repo
git clone --depth 1 https://github.com/maxvaega/skillkit

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

multi-dir-plugin 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.

tests/fixtures/plugins/multi-dir-plugin/.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "manifest_version": "0.1",
  "name": "multi-dir-plugin",
  "version": "2.0.0",
  "description": "Plugin with multiple skill directories",
  "author": {
    "name": "Multi Dir Author"
  },
  "skills": ["skills/", "experimental/"]
}
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. yesterday First seen · 11 lines scan A 8455aaf3e7f8

Subscribe to this mod's changes

multi-dir-plugin is a plugin published in the GitHub repository maxvaega/skillkit (146 stars, last pushed 7mo 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 2026-08-30.

Data and AILLMLangChainTestingagentsaipromptprompt-engineering
Related

Other plugins, from other repositories

awesome-gpt-image-2

Plugin marketplace listing 1 plugin: gpt-image-2-style-library.

freestylefly/awesome-gpt-image-2 · not measured

claude-code

Adrian runtime security: observability and blocking for Claude Code sessions.

secureagentics/Adrian · not measured

adrian

Runtime AI-security tooling for Claude Code and agentic AI, from the Adrian OSS project.

secureagentics/Adrian · not measured

prompt-evaluator

Plugin marketplace listing 1 plugin: prompt-evaluator.

isabela-valonni/prompt-evaluator · not measured

prompt-evaluator

A quiet prompting coach. Scores how you ask, names one thing to sharpen, and remembers your recurring patterns across sessions so the feedback compounds. Works for anyone using AI — not tied to any one domain.

isabela-valonni/prompt-evaluator · not measured

anthropic-agent-skills

Plugin marketplace listing 2 plugins: document-skills, example-skills.

ronniwheellike973/Mini-Agent · not measured