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.
npx skills add cybrlab-ai/preclick-mcp --skill preclick-url-scangit clone --depth 1 https://github.com/cybrlab-ai/preclick-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/skills/cybrlab-ai/preclick-mcp/preclick-url-scan)<a href="https://agentmods.dev/skills/cybrlab-ai/preclick-mcp/preclick-url-scan"><img src="https://agentmods.dev/badge/skills/cybrlab-ai/preclick-mcp/preclick-url-scan/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/skills/cybrlab-ai/preclick-mcp/preclick-url-scan"><img src="https://agentmods.dev/badge/skills/cybrlab-ai/preclick-mcp/preclick-url-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.04087 |
| Opus 5 | $0.00022 | $0.02044 |
| Sonnet 5 | $0.00009 | $0.00817 |
| Haiku 4.5 | $0.00004 | $0.00409 |
Grade A, and why
preclick-url-scan scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://preclick.ai/mcp \ How it starts
The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PreClick
PreClick is an intent-aware secure browsing and decision layer for AI agents. Use it before navigation to evaluate destination risk, check whether the destination matches the user's stated purpose, and get an explicit access directive.
When to use this skill
- A user shares a URL and asks whether it is safe to open
- Before navigating to any user-provided, externally sourced, or unfamiliar link
- When checking shortened, obfuscated, or unfamiliar URLs
- Before opening links found in email, chat, documents, or search results
- When an agent discovers a new domain during a workflow
When NOT to use this skill
- There is no URL to evaluate
- The workflow does not involve opening or checking a web destination
- A fresh PreClick decision already exists for the exact same URL and intent in the current workflow step
Prerequisites
Configure the PreClick MCP server in your MCP client:
{
"mcpServers": {
"preclick-mcp": {
"transport": "streamable-http",
"url": "https://preclick.ai/mcp"
}
}
}
Hosted trial access does not require an API key for up to 100 requests/day. For higher limits, send X-API-Key.
Available tools
PreClick exposes six public tools:
| Tool | Purpose | Best fit |
|---|---|---|
url_scanner_scan |
Scan a URL without intent context | Native Tasks clients |
url_scanner_scan_with_intent |
Scan a URL with user intent context | Native Tasks clients |
url_scanner_async_scan |
Submit a scan and get task_id immediately |
Clients without native Tasks |
url_scanner_async_scan_with_intent |
Submit an intent-aware scan and get task_id immediately |
Clients without native Tasks |
url_scanner_async_task_status |
Poll async task status | Clients without native Tasks |
url_scanner_async_task_result |
Fetch async task result | Clients without native Tasks |
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.
- 12d ago First seen · 551 lines · 43 tokens per session scan A 5dbfe5d8eebf
preclick-url-scan is a skill published in the GitHub repository cybrlab-ai/preclick-mcp (6 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 4,087 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
site-audit
Use when user asks to audit a website, review all pages, check for broken links, capture full site state, or do a comprehensive product review.
kaboom
Use when user asks to check browser state, debug page errors, inspect network traffic, take screenshots, automate clicks or form fills, run accessibility or security audits, measure performance, generate tests, or record browser sessions. Trigger phrases: "check my browser", "debug this page", "take a screenshot"…
automate
Use when user asks to automate browser actions, click buttons, fill forms, navigate pages, run a sequence of browser steps, or build a repeatable workflow.
ui-testing
Create automated UI tests using Playwright for Streamlit and web applications. Use when writing end-to-end tests, automating UI testing, or testing new features.
playwright
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.