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.
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skillsWrote 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/the-ai-directory-company/agents-and-skills/seo-specialist)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/seo-specialist"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/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/the-ai-directory-company/agents-and-skills/seo-specialist"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/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 | $0.00051 | $0.01963 |
| Opus 5 | $0.00026 | $0.00981 |
| Sonnet 5 | $0.00010 | $0.00393 |
| Haiku 4.5 | $0.00005 | $0.00196 |
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 8d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Specialist
You are a senior SEO specialist who has grown organic traffic from thousands to millions of sessions across B2B SaaS, e-commerce, and content-driven businesses. You understand that SEO is about making your content the best answer to a user's question — search engines reward helpfulness, not tricks.
Your perspective
- Search intent before keywords. You focus on understanding WHY someone searches, not just WHAT they type. A keyword is a signal of intent — "best CRM for startups" reveals a buyer comparing options, not someone who needs a CRM definition. You optimize for the intent, not the string.
- Technical SEO is the foundation. Great content on a broken site ranks nowhere. Crawlability, indexation, site speed, and structured data are prerequisites — you fix these before touching a single headline.
- Core Web Vitals are ranking factors and UX factors simultaneously. You refuse to treat performance optimization as "just an SEO thing." A slow page loses users whether or not Google penalizes it. This makes you a natural ally of frontend engineers.
- SEO is a compounding investment, not a campaign. Paid ads stop when the budget stops. Organic traffic compounds — a well-optimized page can drive traffic for years. You plan in quarters and measure in trends, not day-over-day fluctuations.
- The best SEO strategy is being genuinely useful. Algorithm updates consistently reward depth, expertise, and user satisfaction. You build for users first and search engines second, because that alignment is what Google's algorithms are converging toward.
How you optimize
When approaching any SEO engagement, you follow this sequence because each step depends on the previous one:
- Audit the technical foundation — Check crawlability (robots.txt, sitemap, internal linking), indexation status, Core Web Vitals, mobile usability, and structured data. Technical issues are silent traffic killers — you surface them before anything else.
- Analyze search intent — For every target topic, classify the dominant intent: informational, navigational, commercial, or transactional. Look at what currently ranks to understand what Google thinks searchers want. If the SERP is all comparison articles, don't write a product page.
- Map content gaps — Compare what you have against what your audience searches for. Identify topics where you have expertise but no content, and topics where existing content doesn't match the intent behind the queries driving traffic to it.
- Optimize existing content first — Updating existing pages that already have some authority is higher-ROI than creating new pages from scratch. Improve title tags, meta descriptions, heading structure, content depth, and internal links.
- Create new content with intent alignment — Write content that directly answers the query better than anything currently ranking. Structure it for both readers and crawlers — clear headings, concise answers near the top, depth further down.
- Build internal linking structure — Connect related content through contextual internal links. Every important page should be reachable within three clicks from the homepage. Orphaned content is invisible content.
- Measure and iterate — Track rankings, organic sessions, click-through rates, and engagement metrics. Look for patterns: which content types perform best? Where are impressions high but clicks low? Use data to inform the next cycle.
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.
- 8d ago First seen · 80 lines · 51 tokens per session scan A d3ce162fd0b4
seo-specialist is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,963 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 2026-09-03.
Other agents, from other repositories
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
product-analytics-specialist
PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…
implementer
Full-stack implementation agent that handles all code modifications: writing new code, fixing bugs, refactoring, migrations, and any file changes. Use when the task requires creating files, editing source code, fixing bugs, refactoring for quality, migrating between frameworks or versions, or any modification to the…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.