model-guard

model-guard is a plugin for Claude Code from ventusff/claude-model-guard. Its manifest loads nothing; the 2 skills, 1 hook it bundles cost 96 tokens per session together, scanned A, original, MIT.

A Claude Code status line that displays the active model, reasoning effort, thinking state, and rate-limit pressure, with alarms for silent model downgrades. A status line is information shown in the command-line interface while you work.

In plain words
What is it for?
Monitoring model selection, reasoning settings, thinking status, and rate-limit pressure while using Claude Code.
Why use it?
It makes changes in model or usage state visible instead of leaving them unnoticed during a session.

Plugin for Claude Code

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 ventusff/claude-model-guard
agentmods
npx agentmods add plugins/ventusff/claude-model-guard/claude-model-guard
Clone the repo
git clone --depth 1 https://github.com/ventusff/claude-model-guard

Made for: Claude Code.

Wrote 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.

agentmods badge for model-guard

README.md
[![agentmods](https://agentmods.dev/badge/plugins/ventusff/claude-model-guard/claude-model-guard.svg)](https://agentmods.dev/plugins/ventusff/claude-model-guard/claude-model-guard)
Your own site
<a href="https://agentmods.dev/plugins/ventusff/claude-model-guard/claude-model-guard"><img src="https://agentmods.dev/badge/plugins/ventusff/claude-model-guard/claude-model-guard.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 2 skills, 1 hook cost 96 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

model-guard 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 4d 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.

.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "model-guard",
  "displayName": "Model Guard",
  "version": "1.0.0",
  "description": "🚨 Statusline that catches silent model downgrades in Claude Code — theme-proof full-width alarm for model, reasoning effort, thinking state and rate-limit pressure. 8 languages, interactive 30-second setup.",
  "author": {
    "name": "ventusff",
    "url": "https://github.com/ventusff"
  },
  "homepage": "https://github.com/ventusff/claude-model-guard",
  "repository": "https://github.com/ventusff/claude-model-guard",
  "license": "MIT",
  "keywords": [
    "statusline",
    "model",
    "downgrade",
    "alarm",
    "rate-limit",
    "monitor"
  ]
}
Contents

What it installs

The manifest is a name and a version. 2 skills, 1 hook travel with it, and installing the plugin installs all of them — 96 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

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.

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. 4d ago First seen · 22 lines scan A 052c0e310a00

Subscribe to this mod's changes

model-guard is a plugin published in the GitHub repository ventusff/claude-model-guard (1 stars, last pushed 1mo 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.