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 audit-roadmapgit 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/audit-roadmap)<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/audit-roadmap"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/audit-roadmap/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/audit-roadmap"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/audit-roadmap.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 | $0.00168 | $0.01758 |
| Opus 5 | $0.00084 | $0.00879 |
| Sonnet 5 | $0.00034 | $0.00352 |
| Haiku 4.5 | $0.00017 | $0.00176 |
Grade A, and why
audit-roadmap 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 9d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Roadmap — planner: domain -> what to collect
The seo-deep-audit orchestrator immediately runs everything. This skill operates one step
earlier: use quick reconnaissance to create a plan for exactly what to collect for a specific
site, so that expensive work is not run unnecessarily and critical issues are not missed. The
terms-of-reference principle is: "rushing is prohibited" — plan first, collect second.
When to use it
- You were given a domain and asked to analyze it, but the scope/focus is unknown.
- You need a work plan and estimate before starting (for yourself, a client, or a team).
- Before
seo-deep-audit: determine which phases are needed and which should be skipped.
Workflow
Phase 0 — Recon lite (5 commands, a few minutes)
Quick reconnaissance without a crawl. Each item is a single call:
seohead domain-profile --domain <domain> # registration, hosting, ASN, TLS expiry, flags
seohead tech-detect --url https://<domain> # CMS, framework, server, analytics
seohead robots-check --url https://<domain> # what is allowed, sitemap location, junk directives
seohead sitemap-crawl --url https://<domain>/sitemap.xml # scale — number of URLs in the sitemap
seohead ai-bots-check --url https://<domain> # which AI crawlers are allowed
If the sitemap was not found through robots, try /sitemap.xml and /sitemap_index.xml. If the
network or site is unavailable, work with what the user provided (domain, access, objective).
Phase 1 — Interpret signals as categories
Use the Phase 0 output to determine four dimensions — they shape the entire roadmap:
| Dimension | Signals | Decision |
|---|---|---|
| Scale | sitemap: <500 / 500–5,000 / 5,000–50,000 / >50,000 URLs | small -> full analysis; medium -> templates; large -> Dynamic Sampling, near-duplicate analysis required |
| Stack | tech-detect: SPA (React/Vue/Next/Nuxt) vs server rendering (WP/Bitrix/static) |
SPA -> JS rendering (raw vs DOM) + CWV required; static -> JS rendering optional |
| Site type | based on URLs/content: e-commerce / blog-media / services-local / corporate / SaaS / portal | each type -> its own schema set and common issues (see Phase 2) |
| Access and health | TLS expiry <30 days, security D–F, noindex in robots, no llms.txt, retrieval bots blocked | include these in the roadmap's critical tasks |
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.
- 9d ago First seen · 117 lines · 168 tokens per session scan A d4d64490e8a2
audit-roadmap is a skill published in the GitHub repository PavloSEO/seohead-seotools (0 stars, last pushed 6d ago), licensed MIT. It adds 168 tokens to every session and 1,758 once invoked, about $0.0008 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.