Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add imisic/claude-marketplace/plugin install search-visibilityWrote 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/imisic/claude-marketplace/a-seo-gsc)<a href="https://agentmods.dev/skills/imisic/claude-marketplace/a-seo-gsc"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-seo-gsc/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/imisic/claude-marketplace/a-seo-gsc"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-seo-gsc.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 | $0.00029 | $0.03395 |
| Opus 5.5 | $0.00012 | $0.01358 |
| Sonnet 5.5 | $0.00006 | $0.00679 |
| Haiku 4.5 | $0.00003 | $0.00340 |
Grade A, and why
a-seo-gsc 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 5d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
a-seo-gsc: Search Console → action plan
Google Search Console already holds most of the signals for what is wrong with a site's search performance. This skill fetches its Performance data over the API or ingests manual exports, runs a deterministic parser, applies a full analysis playbook (adapting to the site type), and writes a prioritized action plan you can actually execute. It works on any website, not one specific project.
The output is a doc: docs/seo/YYYY-MM-DD-action-plan.md in the target project (or wherever the user keeps analyses), plus a spoken summary of the headline finding and the top moves.
First run: what to give me, and where to get it
Open by asking which route they are on, because both are fully supported and the answer changes only the first step:
Do you have the Search Console API set up for this property, or would you rather download the reports by hand? Both work. The API saves clicking and returns one extra thing the download cannot, but hand-exported CSVs are a first-class input here, not a fallback.
Route A: they have the API, or want it
python3 "${CLAUDE_PLUGIN_ROOT}/skills/a-seo-gsc/scripts/fetch_gsc.py" \
--key "${user_config.gsc_key_file}" --property sc-domain:example.com --days 90
That writes current/ and previous/ directories of CSVs in Google's own export shape. If the property has no service-account key yet, do not hand them a link. Run Setup mode below.
Then ask for the two reports no API serves:
Two exports I cannot fetch, both from Indexing → Pages:
- Click Export on the summary. That gives the indexed vs not-indexed counts and the reason breakdown.
- Click the biggest "not indexed" reason (usually "Crawled - currently not indexed"), then Export the URL table. Repeat for any other large reason. This is the one people skip and the most useful file in the set. Drop the zips in a folder next to the fetched data. Optional extras: the Links report (top linking sites, also no API), Sitemaps, Core Web Vitals, and a screenshot or reading of Performance → Search generative AI (AI Overviews and AI Mode impressions; no API serves it).
What ships with it
7 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.
- 5d ago Changed 66ac1a83384c
- 1mo ago Changed 54b4585acba7
- 2mo ago Changed · +60 lines · +9 tokens per session 2fc53996cef7
- 2mo ago First seen · 81 lines · 20 tokens per session scan A 55345adc3708
a-seo-gsc is a skill published in the GitHub repository imisic/claude-marketplace (1 stars, last pushed 5d ago), licensed MIT. It adds 29 tokens to every session and 3,395 once invoked, about $0.0001 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 2026-08-31.
a-seo-gsc compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| a-seo-gscimisic/claude-marketplace | Skill | 1 | 5d ago | MIT | A | 29 | Claude Code, Codex |
| api-design-reviewerseaworld008/Commonly-used-high-value-skills | Skill | 74 | 5d ago | MIT | A | 34 | Claude Code, Codex |
| python-servicesiliaal/whetstone | Skill | 36 | yesterday | MIT | A | 48 | Claude Code, Codex |
| nodejs-backendiliaal/whetstone | Skill | 36 | yesterday | MIT | A | 50 | Claude Code, Codex |
| meta-reviewing-api-reviewingagents-inc/skills | Skill | 26 | 19d ago | MIT | A | 70 | Claude Code, Codex |
| php-laraveliliaal/whetstone | Skill | 36 | yesterday | MIT | A | 74 | Claude Code, Codex |
| ia-php-laraveliliaal/whetstone | Skill | 36 | yesterday | MIT | A | 67 | Claude Code |