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/agentx402-ai/agentscoutWrote 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/agentx402-ai/agentscout/agentscout)<a href="https://agentmods.dev/plugins/agentx402-ai/agentscout/agentscout"><img src="https://agentmods.dev/badge/plugins/agentx402-ai/agentscout/agentscout/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/agentx402-ai/agentscout/agentscout"><img src="https://agentmods.dev/badge/plugins/agentx402-ai/agentscout/agentscout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agentscout 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "agentscout",
"version": "0.5.3",
"description": "AgentScout: x402-paid web read/extract/crawl for agents. Fetch a URL to clean markdown, extract structured JSON against a schema, or crawl a site — paid per fetch in USDC, no accounts or API keys.",
"license": "MIT",
"author": {
"name": "The AgentScout Authors",
"url": "https://github.com/agentx402-ai/agentscout"
},
"homepage": "https://github.com/agentx402-ai/agentscout",
"userConfig": {
"private_key": {
"type": "string",
"title": "Wallet private key (optional)",
"description": "EVM private key (hex, 0x-prefixed) for the wallet that pays. Leave blank and AgentScout mints + manages a local wallet for you on first use (then fund it).",
"sensitive": true,
"required": false
},
"account_key": {
"type": "string",
"title": "Account key (optional)",
"description": "An ak_ bearer token for managed-wallet (credit) mode. Funded out-of-band via AgentKV. Mutually exclusive with a wallet key.",
"sensitive": true,
"required": false
},
"endpoint": {
"type": "string",
"title": "AgentScout endpoint",
"description": "The AgentScout API endpoint. Defaults to the hosted service.",
"required": false,
"default": "https://api.agentx402.ai"
},
"network": {
"type": "string",
"title": "Network (optional)",
"description": "CAIP-2 network id: eip155:8453 (Base mainnet, default) or eip155:84532 (Base Sepolia testnet).",
"required": false,
"default": "eip155:8453"
},
"max_spend_usd": {
"type": "number",
"title": "Max per-operation spend, USD (optional)",
"description": "Refuse any single operation that would cost more than this. Leave empty for no per-op cap.",
"required": false,
"min": 0
},
"max_session_spend_usd": {
"type": "number",
"title": "Max session spend, USD (optional)",
"description": "Refuse oWhat 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 — 120 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.
- 1mo ago First seen · 63 lines scan A 53e41a80b2fe
agentscout is a plugin published in the GitHub repository agentx402-ai/agentscout (0 stars, last pushed 2d 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
docpull
Pull public web sources into Claude Code. Indexes static and server-rendered sites as local Markdown with conditional-GET caching, then exposes them as MCP tools. Local, browser-free, no API keys.
oxylabs
Oxylabs agent skills bundle: proxies, Web Scraper API, Web Unblocker, Agent Browser, and YouTube video data extraction.
only-cli marketplace
Plugin marketplace listing 1 plugin: only-cli.
only-cli
Browse websites from the terminal in a few hundred tokens.
firecrawl
Search the web, developer sources, and scientific papers with Firecrawl.
firecrawl
Skills and MCP configuration for using the Firecrawl CLI and integrating Firecrawl scrape, search, and interact into apps and agents.