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 marketingskills/seo --skill cannibalization-checkgit clone --depth 1 https://github.com/marketingskills/seoWrote 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/marketingskills/seo/cannibalization-check)<a href="https://agentmods.dev/skills/marketingskills/seo/cannibalization-check"><img src="https://agentmods.dev/badge/skills/marketingskills/seo/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/marketingskills/seo/cannibalization-check"><img src="https://agentmods.dev/badge/skills/marketingskills/seo/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 | $0.00041 | $0.00281 |
| Opus 5 | $0.00020 | $0.00140 |
| Sonnet 5 | $0.00008 | $0.00056 |
| Haiku 4.5 | $0.00004 | $0.00028 |
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 10d 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.
What it actually says
Cannibalization Check
Overview
Analyze GSC query and page data to find situations where multiple pages compete for the same or closely related queries, diluting ranking potential. Recommend consolidation, 301 redirects, or differentiation strategies.
Inputs
- GSC query + page export or live data
- Optional: site content inventory or sitemap
Workflow
- Load GSC data and group queries by semantic similarity.
- For each query group, identify pages that appear for the same query.
- Score cannibalization severity:
- Multiple pages in top 20 for the same query
- Pages splitting clicks/impressions across similar queries
- High-authority page being cannibalized by a lower-authority page
- For each cannibalization instance, recommend:
- Consolidation: 301 to the best page
- Differentiation: adjust targets so pages cover distinct subtopics
- Internal link fix: adjust anchor text and link structure
- Estimate the traffic recovery from resolving each instance.
Output
Cannibalization report with competing page pairs, query overlap, severity score, and fix recommendation.
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.
- 10d ago First seen · 34 lines · 41 tokens per session scan A 5d340f7794b4
cannibalization-check is a skill published in the GitHub repository marketingskills/seo (3 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 281 once invoked, about $0.0002 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
os-check-work
ALWAYS invoke this skill when the user asks about work done outside this session - "check work", "check the others", "check other sessions" - or to accept one: "the session is done, check it", "can we merge it" - in any language. You are the receiving party: treat the report as a claim, verify each part against…
os-done-or-not
ALWAYS invoke this skill when work wraps up or the user asks how it went - "done or not", "are we done", "what happened", "report" - in any language, and when a Stop hook asks for a session report. Produces a ten-line plain- language report: a lead, a checkmark table, and a verdict - fully done, anything needed from…
os-step-by-step
ALWAYS invoke this skill when you need the user to act - run a command, paste a secret, click, approve - and whenever they ask how to do something or say they do not know what to do: "step by step", "walk me through it", "what do I do", "what should I do", "I don't understand what to do", "explain what I need to do"…
os-what-could-go-wrong
ALWAYS invoke this skill before anything hard to undo gets agreed to - a contract, a purchase, a migration, a launch, a price change, a reorganisation - and whenever the user asks "what could go wrong", "what are we missing", "poke holes in this", or for a premortem or a red team, in any language. Assumes the decision…
os-ask-simple
ALWAYS invoke this skill before asking the user any technical question or offering options, and whenever they ask to be asked in plain words - "ask simple", "ask me simply", "ask me in plain words" - or ask if something is worth doing or if something simpler would do, in any language. Rewrites the question in plain…
os-whats-next
ALWAYS invoke this skill when the user asks what to do next, what is left, or what is blocked - "what's next", "what now", "what should we work on", "anything I can do" - in any language. This skill picks the next piece of work; when the user asks HOW to do a thing or says they do not understand what to do, that is…