sf-boundaries

sf-boundaries is a skill for Claude Code from PavloSEO/seohead-seotools. It costs 175 tokens per session (1,863 once invoked), scanned A, original, MIT.

A routing guide for choosing the right tool for an SEO audit request. It explains what Screaming Frog can collect and which checks need another skill or service.

In plain words
What is it for?
Use it to decide how to obtain status codes, metadata, redirects, duplicates, orphan pages, sitemap problems, hosting details, CDN information, and CMS detection.
Why use it?
It prevents wasted work by showing where each type of information comes from, such as crawl data versus hosting or domain data.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to decide how to obtain status codes, metadata, redirects, duplicates, orphan pages, sitemap problems, hosting details, CDN information, and CMS detection.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pavloseo/seohead-seotools/sf-boundaries
Install

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.

Any agent
npx skills add PavloSEO/seohead-seotools --skill sf-boundaries
Clone the repo
git clone --depth 1 https://github.com/PavloSEO/seohead-seotools

Made for: Claude Code.

Wrote 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.

agentmods badge for sf-boundaries

README.md
[![agentmods](https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/sf-boundaries/github.svg)](https://agentmods.dev/skills/pavloseo/seohead-seotools/sf-boundaries)
Your own site
<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/sf-boundaries"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/sf-boundaries/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.

agentmods 80×15 button for sf-boundaries

Your own site · 80×15
<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/sf-boundaries"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/sf-boundaries.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,863 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00175 $0.01863
Opus 5 $0.00088 $0.00932
Sonnet 5 $0.00035 $0.00373
Haiku 4.5 $0.00017 $0.00186

Measured 10d ago against content hash b31e1184a4f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sf-boundaries 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 10d 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 -sI ... | grep -iE 'server|cf-ray|x-powered-by'`.
.claude/skills/sf-boundaries/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SF Boundaries — What to Obtain Through Screaming Frog and What Falls Outside It

SF is a powerful crawler, but it is NOT a universal tool. This skill is a routing map: for each "need," it shows immediately who handles it—SF (through sf-analyzer), a dedicated agent skill, or an external API. Use it BEFORE an audit so you do not try to extract metrics SF does not calculate and do not manually duplicate data that SF provides at no additional cost.

When to Use It

  • "What can/can't Screaming Frog do?", "SF boundaries," or "SF vs agent";
  • "How do I obtain ?"—when the correct tool must be selected;
  • when planning an audit and deciding what to crawl in SF and what to collect separately.

Table: Need -> How to Obtain It

Need How to obtain it
HTTP status codes, redirect chains, response headers SF -> sf-analyzer
Title/Description/meta robots, canonicals, hreflang attributes SF -> sf-analyzer
Duplicates (exact / near-duplicate), Link Score, orphan pages SF -> sf-analyzer (requires Crawl Analysis; see sf-config)
Sitemap: 3xx/4xx URLs in the sitemap, mismatches, stale lastmod SF -> sf-analyzer
Broken links + their DOM location (source/destination/anchor/XPath) SF -> sf-analyzer
HTML-size anomalies, heavy pages SF -> sf-analyzer
WHOIS, domain age, hosting/ASN, geography, TLS toolkit -> seohead domain-profile (seo-recon)
CDN in front of the site, cache behavior, HTTP/2-3, Brotli, TTFB toolkit -> seohead cdn-check (seo-recon)
CMS/framework, analytics, pixels, third-party scripts toolkit -> seohead tech-detect (seo-recon)
Security headers, version disclosure, cookie flags, .git/.env toolkit -> seohead security-check (security-audit)
Backlinks from your own donor list: whether each is live and dofollow toolkit -> seohead backlinks-check (backlinks-check)
JS-rendered vs raw HTML (what a bot sees without JS) agent -> js-render-check
Content quality, meaning, E-E-A-T, expertise manual agent review (SF does not judge meaning)
Silo structure / semantic coverage / topical clusters agent -> silo-audit
Complete H1-H6 outline and its logic agent -> heading-outline
robots.txt analysis and interpretation agent -> robots-audit
PageSpeed / Core Web Vitals (LCP/CLS/INP) external -> PSI API

Read the full file on GitHub · 111 lines

Changes

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.

  1. 10d ago First seen · 111 lines · 175 tokens per session scan A b31e1184a4f3

Subscribe to this mod's changes

sf-boundaries is a skill published in the GitHub repository PavloSEO/seohead-seotools (0 stars, last pushed 7d ago), licensed MIT. It adds 175 tokens to every session and 1,863 once invoked, about $0.0009 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.

Related

Other skills, from other repositories