bing-duplicate-content-fix

bing-duplicate-content-fix is a skill for Codex from TechDivar/bing-webmaster-aeo-mcp. It costs 110 tokens per session (1,389 once invoked), scanned A, original, MIT.

A guarded workflow for finding copied or near-copied articles and pages, including repeated templates, competing pages targeting the same search intent, and keyword cannibalization. It works with public pages, Bing Webmaster tools, and connected WordPress sites.

In plain words
What is it for?
Use it to audit article groups, WordPress categories, or URLs; classify overlap; prepare SEO, answer-engine, and generative-search fixes; apply approved WordPress changes; verify results; and request Bing recrawling when authorized.
Why use it?
It helps distinguish genuine duplication from translations or legitimate reuse, then reduces search confusion without deleting or changing pages without approval.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to audit article groups, WordPress categories, or URLs; classify overlap; prepare SEO, answer-engine, and generative-search fixes; apply approved WordPress changes; verify results; and request Bing recrawling when authorized.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/techdivar/bing-webmaster-aeo-mcp/bing-duplicate-content-fix
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.

Any agent
npx skills add TechDivar/bing-webmaster-aeo-mcp --skill bing-duplicate-content-fix
Clone the repo
git clone --depth 1 https://github.com/TechDivar/bing-webmaster-aeo-mcp

Made for: Codex.

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 bing-duplicate-content-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/techdivar/bing-webmaster-aeo-mcp/bing-duplicate-content-fix/github.svg)](https://agentmods.dev/skills/techdivar/bing-webmaster-aeo-mcp/bing-duplicate-content-fix)
Your own site
<a href="https://agentmods.dev/skills/techdivar/bing-webmaster-aeo-mcp/bing-duplicate-content-fix"><img src="https://agentmods.dev/badge/skills/techdivar/bing-webmaster-aeo-mcp/bing-duplicate-content-fix/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 bing-duplicate-content-fix

Your own site · 80×15
<a href="https://agentmods.dev/skills/techdivar/bing-webmaster-aeo-mcp/bing-duplicate-content-fix"><img src="https://agentmods.dev/badge/skills/techdivar/bing-webmaster-aeo-mcp/bing-duplicate-content-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,389 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 $0.00110 $0.01389
Opus 5 $0.00055 $0.00694
Sonnet 5 $0.00022 $0.00278
Haiku 4.5 $0.00011 $0.00139

Measured 9d ago against content hash 09c976483d20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bing-duplicate-content-fix 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 9d 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.

skills/bing-duplicate-content-fix/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bing Duplicate Content Fix

Use Bing Webmaster, public-page audits, and a connected WordPress tool as one guarded workflow. Treat body similarity as evidence, not a deletion decision. Detect search-intent overlap even when the wording is different.

Read references/decision-rules.md before classifying pages or choosing a fix.

Required workflow

1. Establish the exact inventory

  • Resolve the canonical URLs in scope.
  • For a WordPress category, use category membership or the category ID as the authority. Do not treat a broad text search as complete membership.
  • Separate languages and translated equivalents. A translation is not a duplicate merely because it conveys the same information.
  • Record failed, blocked, redirected, non-indexable, and canonicalized URLs.
  • For more than 30 URLs, divide the inventory into coherent topic groups. Include likely cross-group competitors in both relevant checks.

2. Collect duplication and search evidence

Run aeo_internal_duplicate_check on each URL group:

  • Use 0.82 first to find strong body duplication.
  • Use 0.50 as a second review pass for heavy templates and partial reuse.
  • Do not assume a pair below 0.50 is safe. Intent cannibalization can exist with very low body similarity.

For every plausible competing pair:

  • Compare the SEO title, H1, introduction, headings, tables, FAQs, conclusion, schema, and internal-link anchors.
  • Identify each page's primary user question in one sentence.
  • Use bing_get_page_query_stats or available GSC query-by-page data to see whether the same queries surface both URLs.
  • Use seo_scan_page and aeo_audit_page to check HTTP status, canonical, robots, H1s, metadata, structured data, freshness, internal links, extractability, and intent coverage.
  • Read the latest stored WordPress body and SEO fields before proposing any edit.
  • Treat cached public HTML and authenticated WordPress content as different evidence. State when the public cache is stale or Cloudflare blocks verification.

Read the full file on GitHub · 124 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 124 lines · 110 tokens per session scan A 09c976483d20

Subscribe to this mod's changes

bing-duplicate-content-fix is a skill published in the GitHub repository TechDivar/bing-webmaster-aeo-mcp (1 stars, last pushed 16d ago), licensed MIT. It adds 110 tokens to every session and 1,389 once invoked, about $0.0006 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.