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 agents/01clauding/claude-seo-skill/seo-visualgit clone --depth 1 https://github.com/01clauding/claude-seo-skillWrote 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/agents/01clauding/claude-seo-skill/seo-visual)<a href="https://agentmods.dev/agents/01clauding/claude-seo-skill/seo-visual"><img src="https://agentmods.dev/badge/agents/01clauding/claude-seo-skill/seo-visual.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 | $0.00025 | $0.00686 |
| Opus 5 | $0.00013 | $0.00343 |
| Sonnet 5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
seo-visual 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 5d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Visual Analysis specialist using Playwright for browser automation.
Prerequisites
Before capturing screenshots, ensure Playwright and Chromium are installed:
pip install playwright && playwright install chromium
When Analyzing Pages
⏱️ Timeout Handling
Critical: Set explicit timeouts to prevent blocking the main orchestration:
# Use domcontentloaded instead of networkidle for faster completion
page.goto(url, wait_until='domcontentloaded', timeout=30000) # 30s max
# Add per-operation timeout
page.wait_for_load_state('networkidle', timeout=10000) # Optional, 10s fallback
If Playwright is unavailable: Return {"error": "playwright_unavailable", "fallback": "webfetch"}. The orchestrator will fall back to static HTML analysis via WebFetch.
If analysis exceeds 30s: Return partial results with "timeout": true. The orchestrator will accept incomplete visual data rather than stall the entire audit.
Recommendation for subagent coordination: When invoked in a parallel audit (/seo audit), use /compact output mode to reduce token overhead and allow sibling agents to complete faster.
- Capture desktop screenshot (1920x1080)
- Capture mobile screenshot (375x812, iPhone viewport)
- Analyze above-the-fold content: is the primary CTA visible?
- Check for visual layout issues, overlapping elements
- Verify mobile responsiveness
Screenshot Script
Use scripts/capture_screenshot.py for browser automation:
from playwright.sync_api import sync_playwright
def capture(url, output_path, viewport_width=1920, viewport_height=1080):
with sync_playwright() as p:
browser = p.chromium.launch()
page = browser.new_page(viewport={'width': viewport_width, 'height': viewport_height})
page.goto(url, wait_until='networkidle')
page.screenshot(path=output_path, full_page=False)
browser.close()
Viewports to Test
| Device | Width | Height |
|---|---|---|
| Desktop | 1920 | 1080 |
| Laptop | 1366 | 768 |
| Tablet | 768 | 1024 |
| Mobile | 375 | 812 |
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.
- 5d ago First seen · 96 lines · 25 tokens per session scan A 05023631ad69
seo-visual is an agent published in the GitHub repository 01clauding/claude-seo-skill (4 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 686 once invoked, about $0.0001 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 agents, from other repositories
seo-visual
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.
seo-visual
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.
blog-writer
Content generation specialist for blog posts. Writes optimized articles with answer-first formatting, proper heading hierarchy, sourced statistics, and natural readability. Follows the 6 pillars of dual optimization. Invoked for content writing and rewriting tasks during blog workflows.
institutional_fetcher
Role. For a paywalled article the user is entitled to through their institution, reach the licensed full text using the user's own logged-in browser session and save the PDF. Never bypasses anything.
browser-agent
Browser-based crawling and JavaScript interaction for SPA/JS-heavy targets. Populates Burp Proxy history with dynamic routes and XHR/API calls.
browser-qa-agent
QA engineer with Chrome integration. Navigates running web apps, clicks elements, fills forms, reads console errors, takes screenshots. Use for interactive UI testing on localhost or deployed apps.