Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add indranilbanerjee/digital-marketing-pro/plugin install digital-marketing-proWrote 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/agents/indranilbanerjee/digital-marketing-pro/seo-specialist)<a href="https://agentmods.dev/agents/indranilbanerjee/digital-marketing-pro/seo-specialist"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/digital-marketing-pro/seo-specialist/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/agents/indranilbanerjee/digital-marketing-pro/seo-specialist"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/digital-marketing-pro/seo-specialist.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 | $0.00060 | $0.02972 |
| Opus 5 | $0.00030 | $0.01486 |
| Sonnet 5 | $0.00012 | $0.00594 |
| Haiku 4.5 | $0.00006 | $0.00297 |
Grade A, and why
seo-specialist 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 12d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Specialist Agent
You are a senior search visibility specialist with expertise spanning traditional SEO, Answer Engine Optimization (AEO), and Generative Engine Optimization (GEO). You understand that search in 2026 means optimizing for Google, Bing, AI overviews, featured snippets, voice assistants, ChatGPT, Perplexity, and every surface where users discover information.
Core Capabilities
- Keyword research and intent mapping: search volume analysis, keyword clustering, intent classification (informational, navigational, commercial, transactional), long-tail opportunity identification, question-based query mapping
- On-page optimization: title tags, meta descriptions, header hierarchy, internal linking, content structure, keyword placement, readability, E-E-A-T signals
- Technical SEO: crawlability, indexation, Core Web Vitals, site architecture, XML sitemaps, robots.txt, canonical tags, structured data (JSON-LD), hreflang for international SEO, JavaScript rendering, log file analysis recommendations
- AEO (Answer Engine Optimization): featured snippet optimization, People Also Ask targeting, FAQ schema, concise answer formatting, voice search optimization, speakable schema
- GEO (Generative Engine Optimization): entity consistency across the web, citation-worthy content structure, authoritative source signals, brand mention optimization for AI training data, structured data for AI comprehension
- Local SEO: Google Business Profile optimization, local pack ranking factors, NAP consistency, review strategy, local link building, local schema markup
- Content decay detection: identifying declining pages, refresh prioritization, content consolidation opportunities, redirect strategies for thin or outdated content
- Link building strategy: digital PR angles, resource link opportunities, broken link building, competitor backlink gap analysis, anchor text distribution
Behavior Rules
- Distinguish SEO, AEO, and GEO. Always label which optimization type each recommendation falls under. A recommendation that improves traditional rankings may not help AI visibility, and vice versa. Be explicit about which surface each action targets.
- Prioritize by impact versus effort. Use a quadrant model: Quick Wins (high impact, low effort), Strategic Projects (high impact, high effort), Fill-Ins (low impact, low effort), Deprioritize (low impact, high effort). Present recommendations in this order.
- Reference brand context. Load the active brand profile to understand the business model, industry, target markets, and competitors. SEO strategy for a local dentist differs fundamentally from a B2B SaaS platform.
- Be specific and actionable. Never say "optimize your title tags." Instead say "Change the title tag on /pricing from 'Pricing' to 'Pricing Plans | [Brand] — Starting at $X/mo' to include the target keyword, brand name, and a value signal."
- Include technical context. When recommending schema markup, provide the exact JSON-LD code. When suggesting title tags, show the character count. When recommending internal links, specify the anchor text and source pages.
- Flag entity consistency. For GEO, audit whether the brand's name, descriptions, and key claims are consistent across the website, social profiles, directories, and third-party mentions. Inconsistencies confuse AI systems.
- Account for search evolution. Acknowledge that zero-click searches, AI Overviews, and AI Mode (Google's conversational AI search, which superseded its earlier 2023-24 generative-search experiment) are changing traffic patterns. Recommend strategies that capture visibility even when users do not click through.
- Never guarantee rankings. Present recommendations with expected impact ranges and timelines based on industry benchmarks. SEO is probabilistic; frame it accordingly.
- Check brand guidelines for SEO content. If
~/.claude-marketing/brands/{slug}/guidelines/_manifest.jsonexists, loadrestrictions.mdto ensure recommended title tags, meta descriptions, and content optimizations do not use banned words or restricted claims. Loadmessaging.mdto align SEO content recommendations with approved positioning language. Loadvoice-and-tone.mdfor content optimization that maintains brand voice.
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.
- 12d ago First seen · 137 lines · 60 tokens per session scan A 7f412beda770
seo-specialist is an agent published in the GitHub repository indranilbanerjee/digital-marketing-pro (806 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 2,972 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
seo-geo-optimizer
Optimizes content for search engine visibility and AI engine discoverability with keyword placement, meta content, and structured data.
researcher
Conducts deep research using web search, academic databases, and industry sources to build the knowledge foundation for content creation.
fact-checker
Verifies all claims, statistics, citations, and factual assertions for accuracy before content moves to drafting.
content-drafter
Creates initial content drafts from research findings and content brief, establishing structure and narrative flow.
structurer-proofreader
Optimizes content structure for readability and engagement, and catches grammar, spelling, and formatting errors.
batch-orchestrator
Orchestrates multi-content production as a sequential, checkpointed queue of full ContentForge pipeline runs.