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 skills add PavloSEO/seohead-seotools --skill seo-deep-auditgit clone --depth 1 https://github.com/PavloSEO/seohead-seotoolsWrote 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/pavloseo/seohead-seotools/seo-deep-audit)<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/seo-deep-audit"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/seo-deep-audit/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.
<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/seo-deep-audit"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/seo-deep-audit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00228 | $0.01919 |
| Opus 5 | $0.00114 | $0.00959 |
| Sonnet 5 | $0.00046 | $0.00384 |
| Haiku 4.5 | $0.00023 | $0.00192 |
Grade A, and why
seo-deep-audit 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 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.
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Deep Audit — orchestrator: provide a domain -> get everything
One entry point for a complete audit. When given a domain without a specified scope, work at
maximum depth: run the entire chain of skills and tools yourself, collect everything, and
consolidate it into one report + task plan. Narrow the work only when EXPLICITLY instructed
("only robots," "quick," "lite," "no rendering," "check only headings"). The map of "which tool
retrieves what" is in the sf-boundaries skill.
If you need a plan for exactly what to collect before expensive runs, start with
audit-roadmap(Recon lite -> roadmap with priorities, scale, site type, and YAGNI), and then this skill executes the roadmap.
Default rule
- No scope clarification -> MAX. Run every phase below.
- Explicitly narrowed scope -> only that scope. "only sitemap" -> only the sitemap portion;
"quick/lite" ->
--profile lite+ skip expensive agent-level phases. - Never ask "should I do a full audit?" — a full audit is the default. Clarify only what makes progress impossible (no domain; SF is not installed and no exports are available).
Pipeline (all phases by default)
Phase 0 — Reconnaissance (what kind of site is this?). The seo-recon skill — three toolkit
tools:
seohead domain-profile --domain <domain> # registration, DNS, ASN, geography, TLS, flags
seohead cdn-check --url https://<domain> # CDN + actual cache behavior, HTTP/2-3, TTFB
seohead tech-detect --url https://<domain> # CMS/framework/server, analytics, pixels
Remember the stack: if tech-detect found an SPA/Next.js/Nuxt, mark JS rendering as required
(Phase 2). Some findings from domain-profile.flags and cdn-check.findings go directly into
the report.
Phase 1 — Crawl evidence (96-check registry). SEOHEAD is the analyzer and adapter here, not
the crawler. Check the environment first with seohead sf doctor; live mode requires a separately
installed, actively licensed Screaming Frog CLI.
seohead sf run --crawl https://<domain> --out report --tasks
The full profile is the default (maximum available coverage), and the sitemap is automatically
obtained from robots. The registry contains 96 checks, but only checks supported by the available
exports and enabled SF modules can run. If the output contains many skipped results
(MIXED_CONTENT/STRUCTURED_DATA/SPELLING/DOM_*), enable them once through the sf-config skill
(create audit.seospiderconfig); the tool will pick it up automatically. If SF/a license is not
available, request exports and use mode B (--exports-dir); see sf-analyzer/sf-config.
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.
- 10d ago First seen · 116 lines · 228 tokens per session scan A e8d8917f5df3
seo-deep-audit is a skill published in the GitHub repository PavloSEO/seohead-seotools (0 stars, last pushed 7d ago), licensed MIT. It adds 228 tokens to every session and 1,919 once invoked, about $0.0011 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
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.
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.
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.
competitive-analysis
Analyze AI-search competitors for a query and recommend ranking strategy. Use when users ask competitor analysis, who ranks, or competitive landscape.
validation-doctor
Check Brave Search and Chrome DevTools MCP availability and provide exact setup snippets. Use when validation dependencies are missing or uncertain.
geo-content-research
Researches what prompts people ask AI engines (ChatGPT, Gemini, Perplexity, Claude) about a product category and produces a prompts.csv artifact — a prioritized, strictly-schema'd list of the queries where the brand should be cited. Feeds the monitor workflow.