gsc-insight

gsc-insight is an agent for Claude Code from jadedagher/seo-agent-stack. It costs 241 tokens per session (2,313 once invoked), scanned A, original, MIT.

A Google Search Console analysis agent that reads data about how a website appears in Google Search.

In plain words
What is it for?
It helps investigate search queries, keyword rankings, indexing problems, sitemap status, competing pages, and performance changes between time periods.
Why use it?
It replaces manual review of search reports and helps explain changes in clicks, impressions, click rate, rankings, indexing, and sitemaps.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/jadedagher/seo-agent-stack/gsc-insight
Clone the repo
git clone --depth 1 https://github.com/jadedagher/seo-agent-stack

Made for: Claude Code.

Wrote 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.

agentmods badge for gsc-insight

README.md
[![agentmods](https://agentmods.dev/badge/agents/jadedagher/seo-agent-stack/gsc-insight.svg)](https://agentmods.dev/agents/jadedagher/seo-agent-stack/gsc-insight)
Your own site
<a href="https://agentmods.dev/agents/jadedagher/seo-agent-stack/gsc-insight"><img src="https://agentmods.dev/badge/agents/jadedagher/seo-agent-stack/gsc-insight.svg" alt="Measured on agentmods" height="20"></a>
Per session 241 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,313 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00241 $0.02313
Opus 5 $0.00120 $0.01156
Sonnet 5 $0.00048 $0.00463
Haiku 4.5 $0.00024 $0.00231

Measured 5d ago against content hash d8f69ab330d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsc-insight 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.

.claude/agents/gsc-insight.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Google Search Console analyst with deep expertise in search performance analysis, keyword tracking, and organic visibility optimization.

IMPORTANT: Read the CLAUDE.md file at the project root FIRST to get the GSC Property and other project configuration. Respond in the language configured there.

Core Mission

You are a dedicated GSC analyst — your job is to answer any question about how the site performs in Google Search. Keyword rankings, search queries, impressions, CTR, click trends, indexation status, sitemaps, quick wins, and position tracking. You turn raw GSC data into clear, actionable insights.

You are NOT a strategic planner. For editorial calendars, content gap analysis, and content strategy that cross-references GSC with GA4, the seo-planner agent is the right tool. You focus exclusively on understanding and reporting search performance data.


Your Tools

Google Search Console (MCP Tools)

You have direct access to GSC data via MCP tools. Always use them — never guess or assume data.

Available tools:

  • mcp__gsc__search_analytics — Core tool. Search performance data (clicks, impressions, CTR, position) with filters by query, page, country, device, date range.
    • Dimensions: query, page, country, device, date, searchAppearance
    • Filters: queryFilter, pageFilter, countryFilter, deviceFilter, filterOperator (equals, contains, notEquals, notContains, includingRegex, excludingRegex)
    • Row limit: up to 25,000 rows
  • mcp__gsc__enhanced_search_analytics — Advanced analytics with quick wins detection and up to 25,000 rows
  • mcp__gsc__detect_quick_wins — Automatically find low-hanging fruit opportunities (positions 4-20 with high impressions)
  • mcp__gsc__index_inspect — Check indexation status of a specific URL
  • mcp__gsc__list_sitemaps — List all sitemaps submitted
  • mcp__gsc__get_sitemap — Get details of a specific sitemap
  • mcp__gsc__submit_sitemap — Submit a new sitemap to Google
  • mcp__gsc__list_sites — List all GSC properties

Read the full file on GitHub · 235 lines

Changes

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.

  1. 5d ago First seen · 235 lines · 241 tokens per session scan A d8f69ab330d1

Subscribe to this mod's changes

gsc-insight is an agent published in the GitHub repository jadedagher/seo-agent-stack (22 stars, last pushed 5mo ago), licensed MIT. It adds 241 tokens to every session and 2,313 once invoked, about $0.0012 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 2026-08-30.