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 agentmods add skills/captcha-sonic/agent-skills/captchasonic-setupnpx skills add Captcha-Sonic/Agent-skills --skill captchasonic-setupgit clone --depth 1 https://github.com/Captcha-Sonic/Agent-skillsWrote 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/captcha-sonic/agent-skills/captchasonic-setup)<a href="https://agentmods.dev/skills/captcha-sonic/agent-skills/captchasonic-setup"><img src="https://agentmods.dev/badge/skills/captcha-sonic/agent-skills/captchasonic-setup.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.00781 |
| Opus 5 | $0.00026 | $0.00391 |
| Sonnet 5 | $0.00010 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
captchasonic-setup 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 4d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CaptchaSonic MCP Server Setup
Set up the CaptchaSonic MCP server so your AI agent can solve CAPTCHAs.
Step 1: Check Prerequisites
Verify Node.js is installed (v18+):
node --version
If not installed, the user needs to install Node.js from nodejs.org.
Step 2: Get the API Key
Ask the user for their CaptchaSonic API key. It starts with sonic_.
If they don't have one: "Register for free at captchasonic.com to get your API key."
Step 3: Add the MCP Server
Option A: Claude Code CLI (recommended)
claude mcp add sonic --env SONIC_API_KEY=sonic_xxxx -- npx -y @captchasonic/mcp-server
Replace sonic_xxxx with the user's actual API key.
Option B: Global Install + CLI
npm install -g @captchasonic/mcp-server
claude mcp add sonic --env SONIC_API_KEY=sonic_xxxx -- sonic-mcp
Option C: Claude Desktop
Edit the Claude Desktop config file.
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Add this to the mcpServers section:
{
"mcpServers": {
"sonic": {
"command": "npx",
"args": ["-y", "@captchasonic/mcp-server"],
"env": {
"SONIC_API_KEY": "sonic_xxxx"
}
}
}
}
Then restart Claude Desktop.
Option D: Antigravity IDE
Add MCP server configuration in your Antigravity settings pointing to:
npx -y @captchasonic/mcp-server
with environment variable SONIC_API_KEY=sonic_xxxx.
Step 4: Verify Health Check
After adding the server, run a health check to confirm connectivity:
Tool: health_check
Arguments: {}
Expected response:
healthy: true
version: x.x.x
If the health check fails:
- Check your internet connection
- Verify Node.js is installed and
npxis available - Try running
npx -y @captchasonic/mcp-servermanually to see errors
Step 5: Verify API Key
Run a balance check to confirm the API key is valid:
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.
- 4d ago First seen · 126 lines · 51 tokens per session scan A 133d1baf6557
captchasonic-setup is a skill published in the GitHub repository Captcha-Sonic/Agent-skills (1 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 781 once invoked, about $0.0003 per session on Opus 5. 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 skills, from other repositories
fetch-crawl4ai
Deep URL fetch using crawl4ai (Playwright-powered) for JS-rendered pages, anti-bot sites, and dynamic content. Slower than fetch-jina but handles sites that block simple fetchers. Requires user-installed crawl4ai package.
auto-captcha-solver
Universal captcha auto-solver for Playwright browser automation. Detects hCaptcha and reCAPTCHA v2 on any page, solves via NopeCHA API, and injects tokens automatically. Drop-in CaptchaSolver class with autosolve(page) method.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
2-repro-issue
Reproduce a single LinkedIn-MCP issue locally on the current branch against the real authenticated LinkedIn session at /.linkedin-mcp/profile/, using the MCP streamable-http server. Captures the exact failure mode (tool output, error, missing data) and maps it back to the scraper code path. Use when the user says…