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/StanimirTenev/qrp-mcpWrote 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/stanimirtenev/qrp-mcp/plugin)<a href="https://agentmods.dev/plugins/stanimirtenev/qrp-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/stanimirtenev/qrp-mcp/plugin/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/stanimirtenev/qrp-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/stanimirtenev/qrp-mcp/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
qrp 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 yesterday.
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": "qrp",
"description": "A local cryptographic inventory for developers and AI agents that carries verifiable coverage and its own limits inside the CBOM.",
"icon": "./icon.png",
"version": "0.37.0",
"author": {
"name": "Stanimir Tenev",
"url": "https://quantumreadiness.eu"
},
"homepage": "https://quantumreadiness.eu",
"repository": "https://github.com/StanimirTenev/qrp-mcp",
"license": "Apache-2.0"
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 50 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.
- yesterday Changed 9562515d8dbd
- 4d ago Changed 7fcdd8881142
- 5d ago Changed 40de6bc50423
- 6d ago Changed 3f80c9dec474
- 11d ago Changed 99c9577ce83d
- 13d ago Changed c7d975f09876
- 19d ago Changed 9b42b11dbc35
- 25d ago Changed 43bdecd95f0f
- 26d ago Changed · +1 lines 0f873ec554d9
- 29d ago First seen · 13 lines scan A f2ce79fe052f
qrp is a plugin published in the GitHub repository StanimirTenev/qrp-mcp (2 stars, last pushed yesterday), 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 2026-09-04.
Other plugins, from other repositories
alchemy
Query blockchain data across 100+ chains, simulate transactions, manage Alchemy apps, and work with Solana through the hosted Alchemy MCP server: token balances & prices, NFTs, transfers, transactions, and gas. Does not send, swap, bridge, or pay.
moltnode
MoltNode by Chord: read 31 blockchains over JSON-RPC and swap through Chord (best route, unsigned transaction, simulation), plus Chord's market data and candlestick charts. Two hosted MCP servers and four skills (including a safe swap skill), no API key.
proofledger
Anchor a file's SHA-256 hash on Polygon through the ProofLedger API, save its proof bundle, verify files against bundles offline, and keep agent run receipts: a tamper-evident record of what an agent did that stores only fingerprints. Only hashes leave your machine, plus the file name unless you ask Claude not to send.
nodeflare
Read on-chain data across 23 EVM chains via NodeFlare's public RPC gateway — balances, tokens, transactions, logs and gas.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.