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 ledokter/mcp-gsc --skill cannibalization-checkgit clone --depth 1 https://github.com/ledokter/mcp-gscWrote 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/ledokter/mcp-gsc/cannibalization-check)<a href="https://agentmods.dev/skills/ledokter/mcp-gsc/cannibalization-check"><img src="https://agentmods.dev/badge/skills/ledokter/mcp-gsc/cannibalization-check/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/ledokter/mcp-gsc/cannibalization-check"><img src="https://agentmods.dev/badge/skills/ledokter/mcp-gsc/cannibalization-check.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 | $0.00037 | $0.00298 |
| Opus 5 | $0.00018 | $0.00149 |
| Sonnet 5 | $0.00007 | $0.00060 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
cannibalization-check 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 8d 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.
This is a copy
100% identical to cannibalization-check — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Keyword Cannibalization Check
Identify queries where multiple pages on the same site are competing for rankings.
Steps
- Call
list_propertiesto confirm the exactsite_url. - Call
get_advanced_search_analyticswithdimensions=query,page,sort_by=impressions,row_limit=1000to get all query+page combinations. - Group rows by
query. Queries with two or more distinct pages in the top results are cannibalization candidates. - For each cannibalizing query, collect: both page URLs, their individual clicks, impressions, CTR, and position.
- Sort candidates by total impressions (most valuable cannibalization conflicts first).
- Limit the output to the top 20 most severe cases.
Output format
For each cannibalization case:
- Query: the competing keyword
- Pages: list each URL with its metrics
- Severity: High / Medium / Low based on impressions at stake
- Recommendation: which page to consolidate to (pick the one with better position or CTR), and whether to use a canonical, redirect, or content merge
Present as a markdown table followed by a prioritized action list.
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.
- 8d ago First seen · 29 lines · 37 tokens per session scan A 8ffa01e1c025
cannibalization-check is a skill published in the GitHub repository ledokter/mcp-gsc (0 stars, last pushed 13d ago), licensed MIT. It adds 37 tokens to every session and 298 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cannibalization-check, differing in 0 lines, and is treated as a copy.
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…