Installation
curl -fsSL https://squirrelscan.com/install | bash
iwr -useb https://squirrelscan.com/install.ps1 | iex
~/.local/bin/squirrel and adds it to your PATH.
After installation, run squirrel self doctor to verify everything is set up correctly.
Three Ways to Use squirrelscan
CLI for Humans
AI Agent Skill
Pipe to AI
Run audits directly with human-readable terminal output:squirrel audit example.com
Install the skill for autonomous AI workflows:npx skills install squirrelscan/skills
/audit-website or prompt your AI agent:Use the audit-website skill to audit this site and fix all issues
For best results, use the skill in plan mode if your agent supports it. This lets the agent analyze issues and create an implementation plan before making changes.
Export reports to Claude or other AI assistants:squirrel audit example.com --format llm | claude
See
AI Agent Integration for detailed guidance on using squirrelscan with Claude Code, Cursor, and other AI coding assistants.
Run Your First Audit
Audit a website with a single command:
squirrel audit https://example.com
▄█▀ ▄▀█ █ █ █ █▀▄ █▀▄ █▀▀ █ ▄█▀ ▄▀▀ ▄▀█ █▄ █
▀▄ █ █ █ █ █ ██▀ ██▀ █▀ █ ▀▄ █ █▀█ █ ▀█
█▄▀ ▀▀█ ▀▄▀ █ █ █ █ █ █▄▄ █▄▄ █▄▀ ▀▄▄ █ █ █ █
v0.0.16 (beta) • https://squirrelscan.com
────────────────────────────────────────────
Auditing: https://example.com
Max pages: 500
✓ Audited 12 pages in 2.1s
──────────────────────────────────────────────────
SQUIRRELSCAN REPORT
https://example.com • 12 pages • 72/100 (C)
──────────────────────────────────────────────────
Category Breakdown:
--------------------------------------------------
Core SEO ███████░░░ 75%
Content ████████░░ 82%
Links █████████░ 91%
...
ISSUES
Core SEO (1 error, 3 warnings)
core/meta-description Meta Description (error)
✗ meta-description: Missing meta description
→ /about
→ /contact
core/og-tags Open Graph Tags (warning)
⚠ og-image: Missing og:image
→ /
Content (2 warnings)
content/word-count Word Count (warning)
⚠ word-count: Thin content: 150 words (min 300)
→ /landing
──────────────────────────────────────────────────
87 passed • 12 warnings • 3 failed
──────────────────────────────────────────────────
Common Options
Limit pages crawled
For large sites, limit pages to get faster results:squirrel audit https://example.com -m 10
Export to JSON
Output machine-readable JSON for CI/CD or AI processing:squirrel audit https://example.com -f json -o report.json
Generate HTML report
Create a visual HTML report:squirrel audit https://example.com -f html -o report.html
Fresh crawl
Ignore cache and fetch all pages fresh:squirrel audit https://example.com --refresh
| Format | Flag | Use Case |
|---|
console | (default) | Human-readable terminal output |
json | -f json | CI/CD pipelines, programmatic processing |
html | -f html | Visual reports for sharing |
markdown | -f markdown | Documentation, GitHub |
text | -f text | Plain text output |
llm | -f llm | Compact AI-optimized (40% smaller than XML) |
xml | -f xml | Verbose structured XML for enterprise |
All formats work with both squirrel audit --format and squirrel report --format. The xml format is only available via squirrel report.
Using with AI Agents
squirrelscan is designed for AI workflows. Two primary methods:
1. Install the Skill (Recommended)
npx skills install squirrelscan/skills
Use the audit-website skill to audit example.com and fix all issues
2. Pipe Output to AI
# Audit and pipe directly to Claude
squirrel audit example.com --format llm | claude "analyze and prioritize fixes"
--format llm provides compact, token-optimized output designed specifically for AI agents.
See
AI Agent Integration for advanced workflows including plan mode, subagents, and continuous monitoring.
Next Steps
