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 mirkobozzetto/arsenalnpx agentmods add plugins/mirkobozzetto/arsenal/briefgit clone --depth 1 https://github.com/mirkobozzetto/arsenalWrote 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/mirkobozzetto/arsenal/brief)<a href="https://agentmods.dev/plugins/mirkobozzetto/arsenal/brief"><img src="https://agentmods.dev/badge/plugins/mirkobozzetto/arsenal/brief.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
brief 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": "brief",
"version": "2.2.0",
"description": "Author a product brief by interview (the PRD tradition, under a plainer name), then emit user stories, scope, success metrics, and a derived nested task list. Stops at the task list and hands off.",
"author": {
"name": "Mirko Bozzetto",
"url": "https://github.com/mirkobozzetto"
},
"license": "MIT",
"homepage": "https://github.com/mirkobozzetto/arsenal/tree/main/plugins/brief"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 88 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 12 lines scan A aecb4320ca49
brief is a plugin published in the GitHub repository mirkobozzetto/arsenal (15 stars, last pushed 4d 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
swiftui-animation-match
Match UI/UX interaction needs to proven SwiftUI animation patterns from curated open-source catalogs, with system-first restraint. Ships an analyzed catalog of Shubham0812/SwiftUI-Animations (30 animations + 7 Metal shaders) and a repeatable recipe for cataloging more animation repos.
omnirank
Audit any website across SEO, answer-engine and generative-engine criteria, and generate llms.txt, llms-full.txt and facts.json so AI engines can ingest it as ground truth.
cost-cutter
10 skills that cut your AI bill with proof instead of vibes: cheap/premium routing, advisor call budgets, token receipts audits, tested fallbacks, free-tier batch sizing, guarded cheap swaps, reasoning-effort throttles, evidence-based model bake-offs, context diets, and free-model triage. Every skill carries a…
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.