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 norahe0304-art/30x-seo --skill 30x-seo-cannibalizationgit clone --depth 1 https://github.com/norahe0304-art/30x-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/norahe0304-art/30x-seo/30x-seo-cannibalization)<a href="https://agentmods.dev/skills/norahe0304-art/30x-seo/30x-seo-cannibalization"><img src="https://agentmods.dev/badge/skills/norahe0304-art/30x-seo/30x-seo-cannibalization/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/norahe0304-art/30x-seo/30x-seo-cannibalization"><img src="https://agentmods.dev/badge/skills/norahe0304-art/30x-seo/30x-seo-cannibalization.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 | $0.00043 | $0.01306 |
| Opus 5.5 | $0.00017 | $0.00522 |
| Sonnet 5.5 | $0.00009 | $0.00261 |
| Haiku 4.5 | $0.00004 | $0.00131 |
Grade A, and why
30x-seo-cannibalization 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 1mo 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keyword Cannibalization Detection
Find pages competing for the same keyword
What is Keyword Cannibalization
Problem: Multiple pages on your site targeting the same keyword.
/blog/best-crm-software → Target: "best crm"
/guide/crm-comparison → Target: "best crm"
/products/crm → Target: "best crm"
Consequences:
- Google doesn't know which to rank → none rank well
- Internal link equity is diluted
- Confusing user experience
- Wasted crawl budget
Detection Methods
Method A: With GSC Data (Recommended)
Import GSC "Queries" report
↓
Group by keyword
↓
Find keywords with multiple URLs
↓
Analyze each URL's:
- Impressions
- Clicks
- Average position
- Position fluctuation
↓
Identify cannibalization
Cannibalization Signals:
- Same keyword has 2+ URLs with impressions
- Ranking fluctuates frequently (Google is indecisive)
- Both pages stuck at positions 5-15
Method B: Without GSC Data
Input target keyword list
↓
For each keyword:
- site:domain.com "keyword" search
- Analyze multiple results returned
↓
Check content overlap between pages
↓
Identify potential cannibalization
Output Format
# Keyword Cannibalization Report
## Found X Cannibalization Groups
### Group #1: "best crm software"
| URL | Position | Impressions | Clicks | Content Angle |
|-----|----------|-------------|--------|---------------|
| /blog/best-crm-2024 | #8 | 5,000 | 120 | Review article |
| /guide/crm-comparison | #12 | 3,200 | 45 | Comparison guide |
| /products/crm | #15 | 1,800 | 30 | Product page |
**Diagnosis**: Three pages have different angles but titles/H1s all target "best crm"
**Recommendation**: Differentiation strategy
- /blog/best-crm-2024 → Keep, primary target for "best crm software"
- /guide/crm-comparison → Retarget to "crm comparison guide"
- /products/crm → Retarget to brand term "YourBrand CRM features"
---
### Group #2: "how to use crm"
| URL | Position | Content Overlap |
|-----|----------|-----------------|
| /blog/crm-tutorial | #11 | 80% |
| /help/getting-started | #14 | 75% |
**Diagnosis**: Two pages with highly overlapping content
**Recommendation**: Merge strategy
- Merge into /blog/crm-tutorial (higher traffic)
- 301 redirect /help/getting-started to merged page
- Or: Rewrite /help/getting-started as product-specific tutorial
---
## Solution Summary
| Keyword | Strategy | Keep URL | Action for Others |
|---------|----------|----------|-------------------|
| best crm software | Differentiate | /blog/best-crm-2024 | Update titles |
| how to use crm | Merge | /blog/crm-tutorial | 301 redirect |
| ... | ... | ... | ... |
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.
- 1mo ago First seen · 235 lines · 43 tokens per session scan A f73da9a16997
30x-seo-cannibalization is a skill published in the GitHub repository norahe0304-art/30x-seo (56 stars, last pushed 7mo ago), licensed MIT. It adds 43 tokens to every session and 1,306 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
seo-audit
Single audit entry point — surface-level scorecard or deep infrastructure dive depending on the requested mode. Default full mode produces a multi-layer scorecard across all 9 areas (crawlability, indexation, meta tags, headings, images, Core Web Vitals, JS rendering, mobile + security, structured data, internal…
ai-visibility
Fast-path AI visibility analysis using public web signals, with a per-engine proxy map for ChatGPT, Claude, Gemini, Perplexity, Copilot, and Google AI Overviews. Runs in your Claude Code session without an Akii-hosted score or scoring API. Use when the user asks for "AI visibility", "AI visibility score", "free AI…
optimize-page
Comprehensive single-page optimization across all three layers — traditional SEO (title / meta / H1 / internal links), AEO (chunk quality, direct-answer leads, FAQ extraction), and GEO rewrites using the tactics published by the Princeton/IIT Delhi GEO study (citation integration, expert quotes, statistics enrichment…
broken-links
Find and fix broken links — three modes with different scale ceilings. local audits any local repo (HTML/MD/MDX, no size limit) via Glob/Grep + per-link verification. page checks one live URL deeply (30-100 outbound links per run). site requires the Ahrefs site-audit MCP for true multi-page crawl — without it, refuses…
competitor-intel
Fast-path competitor intelligence — produces a side-by-side SEO + AEO + GEO + AI visibility scorecard plus ranked counter-move plan. Three modes the skill ASKS the user to pick (no default): Quick (10s, surfaces 5 likely competitors from SERPs), Comprehensive (30-60s, multi-source discovery with Ahrefs MCP if…
content-strategy
Fast-path content strategy — produce a pillar + cluster topology, 90-day publishing queue, and quick-win refresh list in a single turn. This is the default for any content-planning question. Use when the user asks to "plan content", "content strategy", "content calendar", "what should I write about", "content gap…