agentmods.dev

semantic-site-auditor

semantic-site-auditor is a skill for Claude Code from siddiqss/semantic-seo-suite. It costs 111 tokens per session (1,099 once invoked), scanned A, original, MIT.

A site review that compares a live website with its planned topic structure, including missing coverage, competing pages, misplaced identity, and pages with no incoming links.

In plain words
What is it for?
Crawling a site, finding content gaps and duplicate topic targeting, detecting orphan pages, and identifying page-level semantic problems.
Why use it?
It turns a broad SEO problem into a prioritised list of issues supported by crawled or derived evidence.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is python ../../scripts/crawl_sitemap.py --domain <domain> --max-pages 500 --out /tmp/urls.json.

Part of the semantic-seo-suite plugin — 10 skills shipped together

not rated 9repo +2 2mo ago A scan 111 tokens original MIT

Good fit Crawling a site, finding content gaps and duplicate topic targeting, detecting orphan pages, and identifying page-level semantic problems.

Compare 6 skills from other repositories ↓
View source ↗ siddiqss/semantic-seo-suite
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/siddiqss/semantic-seo-suite
agentmods
npx agentmods add skills/siddiqss/semantic-seo-suite/semantic-site-auditor

Made for: Claude Code.

Or install semantic-seo-suite, the plugin that ships this one along with the rest of its 10 skills.

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 semantic-site-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/siddiqss/semantic-seo-suite/semantic-site-auditor/github.svg)](https://agentmods.dev/skills/siddiqss/semantic-seo-suite/semantic-site-auditor)
Your own site
<a href="https://agentmods.dev/skills/siddiqss/semantic-seo-suite/semantic-site-auditor"><img src="https://agentmods.dev/badge/skills/siddiqss/semantic-seo-suite/semantic-site-auditor/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 semantic-site-auditor

Your own site · 80×15
<a href="https://agentmods.dev/skills/siddiqss/semantic-seo-suite/semantic-site-auditor"><img src="https://agentmods.dev/badge/skills/siddiqss/semantic-seo-suite/semantic-site-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,099 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00111 $0.01099
Opus 5 $0.00056 $0.00549
Sonnet 5 $0.00022 $0.00220
Haiku 4.5 $0.00011 $0.00110

Measured 11d ago against content hash 751c3af7575b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

semantic-site-auditor 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 11d 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.

skills/semantic-site-auditor/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

semantic-site-auditor

Turn a live site + its topical map into a prioritised, evidence-backed fix list. Every finding carries provenance (measured from crawl, derived from embeddings) — no invented scores. This is also the strongest pre-sales artifact for services work: run it on a prospect's domain before a call.

Read first: ../../framework/topical-map-theory.md (gap/section logic), ../../framework/internal-linking-rules.md (orphans), ../../framework/eav-modeling.md (drift = claimed vs perceived identity).

Preconditions

  • brands/<slug>/config.yaml (tier).
  • A topical-map.json to audit against. If none exists, run topical-map-builder first (you can't measure coverage without a target map).
  • entity-profile.json (for the claimed-identity centroid used by drift).

Workflow

  1. Crawl + extract the site into brands/<slug>/data/crawl/:

    python ../../scripts/crawl_sitemap.py --domain <domain> --max-pages 500 --out /tmp/urls.json
python ../../scripts/extract_page_content.py --urls /tmp/urls.json --out-dir brands/<slug>/data/crawl

    Robustness: crawl_sitemap.py falls back to a same-domain BFS when there's no sitemap, respects robots.txt, and caps pages/depth. For JS-rendered sites, extraction may be thin — note that in the report rather than treating missing content as a gap.

  2. Run the analysis engine:

    python ../../scripts/audit_site.py \
  --map brands/<slug>/topical-map.json --crawl-dir brands/<slug>/data/crawl \
  --entity-profile brands/<slug>/entity-profile.json \
  --locked brands/<slug>/locked-facts.json --brand "<Brand>" \
  --out brands/<slug>/audits/<date>-full.md

    It matches each page to its nearest map node (embedding cosine) and reports:

    • Coverage gaps — nodes with no matching page (derived).
    • Cannibalization — page pairs with high similarity + same intent, and any node hit by multiple pages (derived).
    • Entity drift — pages farthest from the core-section centroid, i.e. content pulling the site away from its claimed identity (derived). At T0 (no embeddings), do this qualitatively and label it asserted — never emit a fake distance.
    • Orphans — pages with no incoming internal links (measured from the crawl link graph).
    • Micro-audit — per-page lint (naked stats, fluff, unanswered question headings) reusing the draft rules.

Read the full file on GitHub · 85 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 85 lines · 111 tokens per session scan A 751c3af7575b

Subscribe to this mod's changes

semantic-site-auditor is a skill published in the GitHub repository siddiqss/semantic-seo-suite (9 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 1,099 once invoked, about $0.0006 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.

Analytics and metricsClaude CodeMarketing and SEOaeoclaude-skillscontent-marketinggenerative-engine-optimizationgeo
Related

Other skills, from other repositories

fire-your-seo-agency

A procedure for improving how a website appears in search engines and how AI answer systems find and cite it. It covers search, answer-engine, generative-AI, and Naver visibility.

leopard627/fire-your-seo-agency · 162 tokens

geo-loop

Run one bounded eGEOagents loop iteration over a workspace domain - read the charter and fresh collector data, do ONE unit of work, write substrate artifacts, append one Timeline entry and one LOG line. Use for loop mode, /geo:loop, scheduled GEO runs, or continuous monitoring.

mverab/eGEOagents · 62 tokens

content-scoring

Score content against the 10 GEO criteria with evidence and prioritized fixes. Use when users ask to score, rate, evaluate, or estimate ranking strength.

mverab/eGEOagents · 34 tokens

schema-generator

Generate JSON-LD schema markup for pages and content types with an implementation checklist. Use when users ask for schema, structured data, rich snippets, or markup.

mverab/eGEOagents · 35 tokens

competitive-analysis

Analyze AI-search competitors for a query and recommend ranking strategy. Use when users ask competitor analysis, who ranks, or competitive landscape.

mverab/eGEOagents · 29 tokens

validation-doctor

Check Brave Search and Chrome DevTools MCP availability and provide exact setup snippets. Use when validation dependencies are missing or uncertain.

mverab/eGEOagents · 28 tokens