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/hanshs474/kavel-mcpWrote 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/hanshs474/kavel-mcp/kavel-mcp)<a href="https://agentmods.dev/plugins/hanshs474/kavel-mcp/kavel-mcp"><img src="https://agentmods.dev/badge/plugins/hanshs474/kavel-mcp/kavel-mcp/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/hanshs474/kavel-mcp/kavel-mcp"><img src="https://agentmods.dev/badge/plugins/hanshs474/kavel-mcp/kavel-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kavel 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 25d 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": "kavel",
"version": "0.1.1",
"description": "Generate AI images with no API key, and find the right Kavel image or video tool with a model-tuned prompt.",
"author": { "name": "Kavel", "url": "https://www.kavel.ai" },
"homepage": "https://www.kavel.ai",
"repository": "https://github.com/hanshs474/kavel-mcp",
"license": "MIT",
"keywords": ["ai", "image-generation", "mcp", "no-api-key"]
}
What it installs
The manifest is a name and a version. 2 skills, 2 MCP servers travel with it, and installing the plugin installs all of them — 177 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.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.
- 25d ago First seen · 11 lines scan A d7d8eba04d31
kavel is a plugin published in the GitHub repository hanshs474/kavel-mcp (0 stars, last pushed 16d 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 2026-10-03.
Other plugins, from other repositories
rosetta-light
Rosetta for Claude - Software Engineering Accelerator instruction set, workflows, and guardrails. (lightweight: simpler workflows, smaller models).
pipeshub
Permissioned search and cited answers over Slack, Drive, Gmail, Jira, Confluence, and 50+ workplace sources, from inside Claude Code.
paparats
Self-hosted semantic code search across all your repos. Search by meaning, follow callers through a symbol graph, and get exact chunks instead of whole files. Runs on your machine; your code never leaves it.
paparats
Self-hosted semantic code search across all your repos. Indexes code with tree-sitter and a local embedding model; nothing leaves your machine.
papi
Persistent project management inside your AI coding tool. PAPI plans what to build next, tracks every decision, and keeps projects coherent across sessions — so a new session starts where the last one left off instead of from nothing.
site-shot
Website screenshots for AI agents: real Chromium, full-page capture, ISO-code country proxies, automatic ad & cookie-banner removal. Wraps the published site-shot-mcp stdio server.