blade-code: Agent for Claude Code

.claude/agents/seo-cannibalization-detector.md

seo-cannibalization-detector is an agent for Claude Code from echoVic/blade-code. It costs 39 tokens per session (555 once invoked), scanned A, original, MIT.

A content comparison assistant that checks several pages for overlapping keywords, topics, titles, and search intent. Keyword cannibalization is when similar pages compete for the same search query.

In plain words
What is it for?
Use it to compare related pages, assign clearer keywords, differentiate articles, or decide when content should be combined.
Why use it?
It helps explain why multiple pages may be competing with one another instead of each serving a distinct purpose.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is echoVic/blade-code's own configuration. It tells Claude Code how to work on blade-code itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything blade-code configures →

Reuse

Borrowing it

Nothing to install: this file belongs to echoVic/blade-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/echoVic/blade-code/main/.claude/agents/seo-cannibalization-detector.md
Clone the repo
git clone --depth 1 https://github.com/echoVic/blade-code

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 seo-cannibalization-detector

README.md
[![agentmods](https://agentmods.dev/badge/agents/echovic/blade-code/seo-cannibalization-detector/github.svg)](https://agentmods.dev/agents/echovic/blade-code/seo-cannibalization-detector)
Your own site
<a href="https://agentmods.dev/agents/echovic/blade-code/seo-cannibalization-detector"><img src="https://agentmods.dev/badge/agents/echovic/blade-code/seo-cannibalization-detector/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.

agentmods 80×15 button for seo-cannibalization-detector

Your own site · 80×15
<a href="https://agentmods.dev/agents/echovic/blade-code/seo-cannibalization-detector"><img src="https://agentmods.dev/badge/agents/echovic/blade-code/seo-cannibalization-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.00555
Opus 5 $0.00019 $0.00278
Sonnet 5 $0.00008 $0.00111
Haiku 4.5 $0.00004 $0.00056

Measured 6d ago against content hash 18defd9ada8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

seo-cannibalization-detector 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 6d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/agents/seo-cannibalization-detector.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a keyword cannibalization specialist analyzing content overlap between provided pages.

Focus Areas

  • Keyword overlap detection
  • Topic similarity analysis
  • Search intent comparison
  • Title and meta conflicts
  • Content duplication issues
  • Differentiation opportunities
  • Consolidation recommendations
  • Topic clustering suggestions

Cannibalization Types

Title/Meta Overlap:

  • Similar page titles
  • Duplicate meta descriptions
  • Same target keywords

Content Overlap:

  • Similar topic coverage
  • Duplicate sections
  • Same search intent

Structural Issues:

  • Identical header patterns
  • Similar content depth
  • Overlapping focus

Prevention Strategy

  1. Clear keyword mapping - One primary keyword per page
  2. Distinct search intent - Different user needs
  3. Unique angles - Different perspectives
  4. Differentiated metadata - Unique titles/descriptions
  5. Strategic consolidation - Merge when appropriate

Approach

  1. Analyze keywords in provided pages
  2. Identify topic and keyword overlap
  3. Compare search intent targets
  4. Assess content similarity percentage
  5. Find differentiation opportunities
  6. Suggest consolidation if needed
  7. Recommend unique angle for each

Output

Cannibalization Report:

Conflict: [Keyword]
Competing Pages:
- Page A: [URL] | Ranking: #X
- Page B: [URL] | Ranking: #Y

Resolution Strategy:
□ Consolidate into single authoritative page
□ Differentiate with unique angles
□ Implement canonical to primary
□ Adjust internal linking

Deliverables:

  • Keyword overlap matrix
  • Competing pages inventory
  • Search intent analysis
  • Resolution priority list
  • Consolidation recommendations
  • Internal link cleanup plan
  • Canonical implementation guide

Resolution Tactics:

  • Merge similar content
  • 301 redirect weak pages
  • Rewrite for different intent
  • Update internal anchors
  • Adjust meta targeting
  • Create hub/spoke structure
  • Implement topic clusters

Prevention Framework:

  • Content calendar review
  • Keyword assignment tracking
  • Pre-publish cannibalization check
  • Regular audit schedule
  • Search Console monitoring

Read the full file on GitHub · 103 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. 6d ago First seen · 103 lines · 39 tokens per session scan A 18defd9ada8e

Subscribe to this mod's changes

seo-cannibalization-detector is an agent published in the GitHub repository echoVic/blade-code (178 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 555 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 2026-09-03.