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 russjeffery/google-search-console-mcp --skill google-search-consolegit clone --depth 1 https://github.com/russjeffery/google-search-console-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/russjeffery/google-search-console-mcp/google-search-console)<a href="https://agentmods.dev/skills/russjeffery/google-search-console-mcp/google-search-console"><img src="https://agentmods.dev/badge/skills/russjeffery/google-search-console-mcp/google-search-console/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/russjeffery/google-search-console-mcp/google-search-console"><img src="https://agentmods.dev/badge/skills/russjeffery/google-search-console-mcp/google-search-console.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 | $0.00080 | $0.01654 |
| Opus 5 | $0.00040 | $0.00827 |
| Sonnet 5 | $0.00016 | $0.00331 |
| Haiku 4.5 | $0.00008 | $0.00165 |
Grade A, and why
google-search-console 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Search Console
Analysis over the Search Console API via the google-search-console-mcp server.
The API is small, but its data has four properties that produce confidently wrong answers if you don't account for them. Most of this skill is about those.
Always start with list_sites
Every tool needs an exact siteUrl, and Search Console treats these as
completely different properties with different data:
| Form | Meaning |
|---|---|
https://example.com/ |
URL-prefix property. Scheme matters, trailing slash required. |
http://example.com/ |
A different property from the https one. |
sc-domain:example.com |
Domain property. Covers all subdomains and both schemes. |
Never construct one from a bare domain the user mentioned. List them and match.
permissionLevel also tells you what will work: siteOwner and siteFullUser
can do everything here; siteRestrictedUser has limited data access;
siteUnverifiedUser cannot read data at all.
The four things that cause wrong answers
1. Data lags about three days. Search Console does not finalise data
immediately. Query a window ending today and you will see a sharp fake decline
in the last few days and may report a crisis that does not exist. Use the
lastDays argument — the tools then pick a safe window automatically. Only use
explicit startDate/endDate when the specific window matters, and end it at
least 3 days back.
2. Query data is privacy-filtered. When you group by query, Google
silently omits rare queries that could identify individuals. Consequences:
- Query-level clicks will not sum to the property total. That gap is not lost traffic, not a tracking bug, and not worth investigating.
- Only ever compare query-level sums against other query-level sums.
- A query "appearing" or "disappearing" between periods may just have crossed the visibility threshold.
3. Position is inverted. Position 3 is better than position 8. A negative
change in position is an improvement. compare_search_analytics returns an
explicit improved boolean — use it rather than reasoning about the sign.
What ships with it
3 files 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.
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 · 155 lines · 80 tokens per session scan A f56e6e188460
google-search-console is a skill published in the GitHub repository russjeffery/google-search-console-mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 80 tokens to every session and 1,654 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…