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.
/plugin marketplace add amIT-nitb/claude-calloutnpx agentmods add plugins/amit-nitb/claude-callout/claude-calloutgit clone --depth 1 https://github.com/amIT-nitb/claude-calloutWrote 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/amit-nitb/claude-callout/claude-callout)<a href="https://agentmods.dev/plugins/amit-nitb/claude-callout/claude-callout"><img src="https://agentmods.dev/badge/plugins/amit-nitb/claude-callout/claude-callout.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
claude-callout 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 5d 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": "claude-callout",
"version": "0.5.2",
"description": "Voice + OS notifications when Claude is waiting on you or finished a turn. Cross-platform, focus-aware, with quiet hours and 10s debounce to keep noise low.",
"author": {
"name": "Amit Singh",
"url": "https://github.com/amIT-nitb"
},
"homepage": "https://github.com/amIT-nitb/claude-callout",
"repository": "https://github.com/amIT-nitb/claude-callout",
"keywords": ["voice", "notification", "tts", "hooks", "accessibility", "claude-code-plugin"],
"license": "MIT"
}
What it installs
The manifest is a name and a version. 10 commands, 4 hooks travel with it, and installing the plugin installs all of them — 171 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command voice-status A 13 tokens
- Command voice-mute A 20 tokens
- Command voice-test A 22 tokens
- Command voice-off A 15 tokens
- Command voice-on A 15 tokens
- Command voice-when-focused-off A 16 tokens
- Command voice-when-focused-on A 22 tokens
- Command notify-off A 16 tokens
- Command notify-on A 16 tokens
- Command voice-unmute A 16 tokens
- Hook Stop A not measured
- Hook Notification A not measured
- Hook UserPromptSubmit A not measured
- Hook SessionStart A not measured
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.
- 5d ago First seen · 14 lines scan A 491656f66040
claude-callout is a plugin published in the GitHub repository amIT-nitb/claude-callout (1 stars, last pushed 2mo 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.
Other plugins, from other repositories
cloudflare-browser-rendering
Cloudflare Browser Rendering with Puppeteer/Playwright. Use for screenshots, PDFs, web scraping, or encountering rendering errors, timeout issues, memory exceeded.
cloudflare-cron-triggers
Cloudflare Cron Triggers for scheduled Workers execution. Use for periodic tasks, scheduled jobs, or encountering handler not found, invalid cron expression, timezone errors.
voice-to-claude
High-quality voice dictation for Claude Code using whisper.cpp with Metal GPU acceleration.
hyperfocus
ADHD-friendly output formatting. Restructures responses with evidence-based cognitive accessibility: chunking, visual hierarchy, front-loaded key points, and progressive disclosure.
squirrel
A status line for Claude Code, built for ADHD brains: context, usage limits, git state, and an alarm you cannot miss when Claude is waiting on you.
status-icons
Marks the terminal tab with an icon that tells "it is done" apart from "it is blocked on you", where Claude Code shows the same star for both.