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 PavelUngr/seznam-webmaster-mcp --skill seznam-webmastergit clone --depth 1 https://github.com/PavelUngr/seznam-webmaster-mcpWrote 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/pavelungr/seznam-webmaster-mcp/seznam-webmaster)<a href="https://agentmods.dev/skills/pavelungr/seznam-webmaster-mcp/seznam-webmaster"><img src="https://agentmods.dev/badge/skills/pavelungr/seznam-webmaster-mcp/seznam-webmaster/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/pavelungr/seznam-webmaster-mcp/seznam-webmaster"><img src="https://agentmods.dev/badge/skills/pavelungr/seznam-webmaster-mcp/seznam-webmaster.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 | $0.00076 | $0.01487 |
| Opus 5.5 | $0.00030 | $0.00595 |
| Sonnet 5.5 | $0.00015 | $0.00297 |
| Haiku 4.5 | $0.00008 | $0.00149 |
Grade A, and why
seznam-webmaster 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seznam Webmaster
Seznam.cz is the second-largest search engine in the Czech Republic and Seznam Webmaster is its equivalent of Google Search Console. This skill explains how to use the seznam-webmaster-mcp tools correctly and how to interpret what they return.
Prerequisites
- The MCP server
@pavelungr/seznam-webmaster-mcpmust be configured in the client. If its tools are not available, tell the user to install it (https://github.com/PavelUngr/seznam-webmaster-mcp). Depending on the client, tool names may carry a prefix with the server name. - Every website has its own API key and the key decides which website the data belongs to. There is no account-wide key and no way to list all sites of an account. The agent only sees the domains the user configured, so a site that is missing from
list_sitesneeds its key added to the server configuration. - Never ask the user to paste an API key into the chat and never print one. Keys live in the client configuration and no tool returns them.
Tools
| Tool | Use it for |
|---|---|
list_sites |
Lists the configured domains. Call it first when the user did not name a domain or when you are unsure which domains exist. |
get_web_status |
One-call overview: counts per category plus the daily history. |
get_indexed_pages |
Counts per category plus a random sample of up to 1000 URLs per category. |
get_index_history |
Daily counts. Optional date_from and date_to in YYYY-MM-DD, date_from must not be later than date_to. |
get_document_info |
Details of one URL: title, meta tags, Open Graph data, response headers, flags isIndexed, isError, isRedirect, and timestamps. |
reindex_url |
Requests reindexing of one URL. Needs a key with write access. |
get_database_info |
Release marker of Seznam's database (looks like a timestamp). Needs no key and no domain. |
Notes on the domain argument, which is the first argument of every tool except list_sites and get_database_info:
- Use the configured domain. A scheme, path, port or trailing dot is stripped, so
https://example.cz/matchesexample.cz. www.is not stripped.www.example.czandexample.czare different entries.urlarguments must be absolutehttporhttpsURLs and must belong to the site the key belongs to.
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 · 81 lines · 76 tokens per session scan A 99d83c83ed3d
seznam-webmaster is a skill published in the GitHub repository PavelUngr/seznam-webmaster-mcp (5 stars, last pushed 10d ago), licensed MIT. It adds 76 tokens to every session and 1,487 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-20.
Other skills, from other repositories
cannibalization-check
Detect keyword cannibalization — queries where multiple pages compete for the same rankings. Use when asked about competing pages, keyword overlap, or cannibalization.
content-opportunities
Find quick-win content optimization targets — high impressions, low CTR, position 11-20. Use when asked for content ideas or optimization opportunities.
indexing-audit
Audit indexing status across top pages. Use when asked about crawling, indexing issues, or whether pages are indexed by Google.
seo-weekly-report
Generate a complete weekly SEO performance report for a site. Use when asked for a site summary, performance overview, or weekly report.
sklik-ppc
Create and optimize Sklik PPC search and display campaigns. Keyword research, ad copy, banner management, and campaign structure.
grade-a-site
Grade any public URL for agent-readability across 20 checks and get paste-ready fixes. Use when asked whether a site is readable by AI agents, why an agent cannot use a site, or how to make a site discoverable to LLMs and agents.