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/LukeRenton/explore-claude-codeWrote 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/lukerenton/explore-claude-code/marketplace)<a href="https://agentmods.dev/plugins/lukerenton/explore-claude-code/marketplace"><img src="https://agentmods.dev/badge/plugins/lukerenton/explore-claude-code/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/lukerenton/explore-claude-code/marketplace"><img src="https://agentmods.dev/badge/plugins/lukerenton/explore-claude-code/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
explore-claude-code 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
// .claude-plugin/marketplace.json — Marketplace Catalogue
//
// This file defines a plugin marketplace: a catalogue that lists
// plugins and tells Claude Code where to fetch them. Host this
// in a git repo and share it with your team or community.
//
// Users add your marketplace:
// /plugin marketplace add owner/repo
//
// Then install individual plugins:
// /plugin install review-plugin@my-marketplace
// ── Marketplace identity ───────────────────────────────────────
// Public-facing name (kebab-case). Users see this when installing:
// /plugin install <plugin>@my-marketplace
"name": "my-marketplace",
// Who maintains this marketplace
"owner": {
"name": "Your Team",
"email": "[email protected]"
},
// ── Optional metadata ──────────────────────────────────────────
"metadata": {
"description": "A starter marketplace showing the catalogue format",
"version": "1.0.0",
// Base directory for relative plugin sources.
// With this set, "source": "review-plugin" resolves to "./plugins/review-plugin"
"pluginRoot": "./plugins"
},
// ── Plugin catalogue ───────────────────────────────────────────
//
// Each entry needs at minimum a name and source.
// You can also include any field from the plugin.json schema.
"plugins": [
// ── Relative path source ─────────────────────────────────────
// Plugin lives in the same repo as the marketplace.
// The simplest option for self-contained marketplaces.
{
"name": "review-plugin",
"source": "./plugins/review-plugin",
"description": "Adds a /review skill for quick code reviews",
"version": "1.0.0"
},
// ── GitHub source ────────────────────────────────────────────
// Plugin lives in a separate GitHub repo.
// Supports ref (branch/tag) and sha (exact commit) pinning.
{
"name": "deploy-tools",
"source": {
"source": "github",
"repo": "your-org/deploy-pluginWhat 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 · 92 lines scan A ba9bee0ceb60
explore-claude-code marketplace is a plugin published in the GitHub repository LukeRenton/explore-claude-code (320 stars, last pushed 12d 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 2026-08-30.
Other plugins, from other repositories
master-skill
A collection of Buddhist AI assistant skills based on Buddhist texts and commentaries, covering teachers and traditions from India, China, Tibet, and Theravāda Buddhism.
daily
Day-to-day skills with memory: a morning briefing, a tutor that remembers what you got wrong, and a retro that turns agent mistakes into one-line fixes.
reader-comprehension-pass
Check what a reader can recover from the visible material, identify missing prerequisites, and preserve technical meaning during revision.
roleplay
Plugin รวม Skills สำหรับ Role-Play และการจำลองสถานการณ์ ครอบคลุม การสอบสวน, การสัมภาษณ์งาน และผู้ช่วยยุทธศาสตร์ระดับประเทศ.
unabatedpm-career-growth
AI coaching skills for PM career development — resume design, job search strategy, interview coaching, career transitions, confidence building, negotiation, and navigating AI's impact on the profession. Each skill coaches you through real frameworks with scoring rubrics, persona archetypes, and pushback on generic…
unabatedpm-strategic-thinking
AI coaching skills for PM strategic thinking — role clarity, vision synthesis, strategy articulation, and stakeholder management. Each skill coaches you through the thinking with scoring rubrics, real coaching exchanges, and pushback on weak reasoning.