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/debytesio/claude-pluginsWrote 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/debytesio/claude-plugins/marketplace)<a href="https://agentmods.dev/plugins/debytesio/claude-plugins/marketplace"><img src="https://agentmods.dev/badge/plugins/debytesio/claude-plugins/marketplace/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/debytesio/claude-plugins/marketplace"><img src="https://agentmods.dev/badge/plugins/debytesio/claude-plugins/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
debytes marketplace 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 1mo 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
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "debytes",
"owner": {
"name": "DeBytes",
"email": "[email protected]"
},
"metadata": {
"description": "AI-powered plugins by DeBytes — cloud tools for job search, trading, e-commerce, and more.",
"version": "1.0.0"
},
"plugins": [
{
"name": "job-hunter",
"description": "AI-powered job search across UK and France platforms with visa sponsorship checking, salary analysis, and ranked Excel exports.",
"version": "1.1.0",
"author": {
"name": "DeBytes",
"email": "[email protected]",
"url": "https://debytes.io"
},
"source": {
"source": "url",
"url": "https://github.com/debytesio/claude-plugin-jobhunter.git"
},
"homepage": "https://debytes.io/products/cloud",
"repository": "https://github.com/debytesio/claude-plugin-jobhunter",
"license": "Apache-2.0",
"category": "productivity",
"keywords": ["jobs", "recruitment", "career", "salary", "visa", "ukvi", "deb-cloud"]
}
]
}
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.
- 1mo ago First seen · 34 lines scan A 6407ec7fdf59
debytes marketplace is a plugin published in the GitHub repository debytesio/claude-plugins (3 stars, last pushed 6mo ago), licensed Apache-2.0. 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
jobxhunter
Build a master profile from your own files, tailor ATS-safe CVs to any job description, source live UK and Canada roles, write cover letters, and track every application.
telegram-topics
Telegram channel for Claude Code — 1 project = 1 forum topic, with a live working/idle status badge on each topic. Run multiple projects concurrently, get notifications, and drive or approve sessions remotely from your phone. Configure with /telegram-topics:configure.
soheil-jobxhunter marketplace
Job-hunting tooling for the UK and Canada: profile intake, ATS-safe CV tailoring, sourcing, cover letters, and application tracking.
claude-pet
A desktop companion (Windows) that watches your Claude Code sessions and tells you - with status cards and a soft chime - when Claude is thinking, needs your input, or is done - and flags a card that's still running a background task. Hover a card to see everything.
token-efficiency-coach
Finds where a Claude Code session wasted tokens (uncached context, context bloat, oversized tool output, redundant reads, wrong-tier routing) and coaches the fix. Adds a live cost/context statusline and a non-blocking end-of-session coach.
cli-autocomplete
Generate shell autocompletion scripts.