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.
git clone --depth 1 https://github.com/automagik-dev/genieWrote 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/automagik-dev/genie/claude-code)<a href="https://agentmods.dev/plugins/automagik-dev/genie/claude-code"><img src="https://agentmods.dev/badge/plugins/automagik-dev/genie/claude-code/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/automagik-dev/genie/claude-code"><img src="https://agentmods.dev/badge/plugins/automagik-dev/genie/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mikro 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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "mikro",
"displayName": "mikro",
"version": "0.1.0",
"description": "Registers the mikro MCP server against the current project, so every agent.yaml microagent in the workspace becomes a callable tool.",
"author": {
"name": "Automagik",
"url": "https://github.com/automagik-dev/mikro"
},
"homepage": "https://github.com/automagik-dev/mikro/tree/main/plugins/claude-code",
"repository": "https://github.com/automagik-dev/mikro",
"license": "MIT",
"keywords": [
"mikro",
"mcp",
"microagent",
"offload"
],
"skills": [
"./skills/offload-guidance",
"./skills/microagent-create"
]
}
What it installs
The manifest is a name and a version. 2 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 461 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 25 lines scan A 7e5b2d024df1
mikro is a plugin published in the GitHub repository automagik-dev/genie (346 stars, last pushed today), 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 2026-10-16.
Other plugins, from other repositories
stash
Connect Claude Code to Stash — stream activity to your Stash and collaborate with your other agents.
faf
Persistent Project Context for AI — IANA-registered .faf format. Run /faf to score your project in Claude Code; install the CLI via bunx faf or npm install -g faf-cli for the full toolkit.
claude-slim
Analyze and reduce Claude Code token overhead.
atomicmemory
Persistent semantic memory for Claude Code — user preferences, project context, prior decisions, and codebase facts that survive across sessions.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.