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 site-reportgit 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/site-report)<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/site-report"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/site-report/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/site-report"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/site-report.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 | $0.00134 | $0.01127 |
| Opus 5 | $0.00067 | $0.00563 |
| Sonnet 5 | $0.00027 | $0.00225 |
| Haiku 4.5 | $0.00013 | $0.00113 |
Grade A, and why
site-report 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site Report — From Domain to File
The consolidation is implemented in code: one call assembles the evidence document, and a second call turns it into a file.
Workflow
Everything at once — audit and Excel in a single command:
seohead site-audit --url https://example.com --limit 50 --report xlsx --out audit.xlsx
Two steps when multiple reports are needed:
seohead site-audit --url https://example.com --limit 100 > audit.json
seohead report-build --audit audit.json --format docx --out client.docx
seohead report-build --audit audit.json --format csv --out tasks.csv
A custom page list instead of the sitemap (for example, landing pages from the semantic keyword set):
seohead site-audit --url https://example.com --urls "https://example.com/a,https://example.com/b"
What Runs
| Level | Tools | Number of Runs |
|---|---|---|
| Site | domain, CDN and cache, stack, security, robots, AI crawlers, llms.txt, regions, rendering, sitemap | once |
| Page | parse, schema-check, social-meta-check |
for every URL |
The URL list comes from the sitemap, whose address is read from robots.txt. If
there is no sitemap, at least the home page is analyzed, and this is reflected in
pages_checked.
Flags That Actually Change the Result
| Flag | When It Is Needed |
|---|---|
--limit N |
25 pages by default. Increase it deliberately on a large site: this generates N×3 requests |
--concurrency N |
5 by default, with a ceiling of 10. The audit must not resemble a load test |
--render |
a script renders the city switcher (requires Playwright) |
--skip |
avoid unnecessary checks: --skip render_check,regions_check |
How to Read the Result
Start with summary.tools_failed. This is the most important field: it lists
the checks that did not run successfully. Their silence does not mean "no issues
found." All four formats print this block separately, and the report should be read
starting with it.
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.
- 11d ago First seen · 102 lines · 134 tokens per session scan A 82141573d52a
site-report is a skill published in the GitHub repository PavloSEO/seohead-seotools (0 stars, last pushed 8d ago), licensed MIT. It adds 134 tokens to every session and 1,127 once invoked, about $0.0007 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
xlsx
Create, inspect, edit, restructure, convert, and validate XLSX workbooks and CSV files using Qubicl's pinned local spreadsheet tools. Use for formulas, tables, charts, formatting, workbook structure, and CSV interoperability.
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.
tencent-docs
A skill for creating, reading, editing, searching, and managing Tencent Docs, an online document and spreadsheet service.
lark-base
A guide for managing Lark Base, Feishu's spreadsheet-like database and workspace tool. It covers tables, fields, records, views, formulas, forms, dashboards, applications, workflows, and permissions.
visualizer
A skill for turning structured data, spreadsheets, and business metrics into HTML charts and dashboards using Chart.js, a JavaScript charting library.
liteparse
Parse documents into LLM-ready content entirely on the local machine — PDF / DOCX / XLSX / PPTX / images → Markdown, structured JSON (with bounding boxes), or page screenshots, via the lit CLI. No cloud, no LLM, works offline. Use whenever the user attaches or points to a document that must be read before reasoning…