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/anthony-chaudhary/dos-kernelWrote 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/anthony-chaudhary/dos-kernel/gemini-extension)<a href="https://agentmods.dev/plugins/anthony-chaudhary/dos-kernel/gemini-extension"><img src="https://agentmods.dev/badge/plugins/anthony-chaudhary/dos-kernel/gemini-extension/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/anthony-chaudhary/dos-kernel/gemini-extension"><img src="https://agentmods.dev/badge/plugins/anthony-chaudhary/dos-kernel/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dos-kernel 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": "dos-kernel",
"version": "0.30.0",
"description": "The kernel that doesn't believe the agents. Exposes the DOS trust syscalls as MCP tools — verify what actually shipped (git ancestry, not self-report), arbitrate file-tree collisions before two agents edit the same files, and refuse with a structured reason from a closed vocabulary. Requires the dos-kernel Python package: pip install 'dos-kernel[mcp]'.",
"contextFileName": "GEMINI.md",
"mcpServers": {
"dos": {
"command": "python",
"args": ["-m", "dos_mcp.server"],
"cwd": "${extensionPath}",
"env": {
"PYTHONIOENCODING": "utf-8"
}
}
}
}
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 · 17 lines scan A 9f0a34f8bdf5
dos-kernel is a plugin published in the GitHub repository anthony-chaudhary/dos-kernel (19 stars, last pushed yesterday), 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 2026-09-07.
Other plugins, from other repositories
claude-powerline
Claude Powerline statusline setup wizard.
loop-orchestrator marketplace
Marketplace for loop-orchestrator — a methodology-grounded multi-session orchestrator plugin for Claude Code.
humanizer
Rewrite AI-sounding text so it reads naturally 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.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.