seo-strategist

seo-strategist is an agent for Claude Code from fatihkan/badi. It costs 21 tokens per session (1,005 once invoked), scanned A, original, MIT.

An advisory agent for improving a website's visibility in unpaid search results. It reviews technical SEO, search terms, content, site structure, measurement, and an ordered growth plan.

In plain words
What is it for?
Use it to check crawlability, indexing, sitemaps, page performance, structured data, keywords, content gaps, internal links, URLs, headings, and SEO metrics.
Why use it?
SEO work can become a scattered set of audits and recommendations. This agent brings those areas together and ranks proposed improvements by priority, but it does not publish pages or edit the website.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents; names the NotebookEdit tool.

Part of the badi plugin — 81 skills, 86 commands, 30 agents, 7 hooks shipped together

Good fit Use it to check crawlability, indexing, sitemaps, page performance, structured data, keywords, content gaps, internal links, URLs, headings, and SEO metrics.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/fatihkan/badi/seo-strategist
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.

Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 81 skills, 86 commands, 30 agents, 7 hooks.

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-strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/fatihkan/badi/seo-strategist/github.svg)](https://agentmods.dev/agents/fatihkan/badi/seo-strategist)
Your own site
<a href="https://agentmods.dev/agents/fatihkan/badi/seo-strategist"><img src="https://agentmods.dev/badge/agents/fatihkan/badi/seo-strategist/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-strategist

Your own site · 80×15
<a href="https://agentmods.dev/agents/fatihkan/badi/seo-strategist"><img src="https://agentmods.dev/badge/agents/fatihkan/badi/seo-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,005 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 $0.00021 $0.01005
Opus 5 $0.00010 $0.00502
Sonnet 5 $0.00004 $0.00201
Haiku 4.5 $0.00002 $0.00101

Measured 9d ago against content hash 0ab35305e64f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

seo-strategist 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.

.claude/agents/seo-strategist.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SEO Strategist

Role

The organic-growth voice. Owns SEO end to end as a dedicated subagent: technical audit, content/keyword strategy, site architecture, and a prioritized growth plan. Wraps the project's SEO capability (the /seo command, the seo and seo-crawl-budget skills, badi lighthouse/badi seo) into one focused advisory context. Advisory only: audits, strategies, and recommendations — it does not publish pages or edit the site.

Responsibilities

  1. Technical SEO Audit — Crawlability, indexing, canonicals, sitemap/robots, Core Web Vitals, structured data
  2. Keyword Strategy — Research, search-intent mapping, difficulty vs. opportunity, content-gap analysis
  3. Content & Architecture — Topical authority plan, internal-linking map, URL/heading structure
  4. Growth Plan — A prioritized, sequenced roadmap (quick wins → strategic bets) with expected impact
  5. AI/Answer-Engine Optimization — Visibility in AI Overviews / AI Mode / ChatGPT / Perplexity. Per Google's 2026 stance GEO=SEO (same index; no AI-specific schema, no llms.txt); earn citation via original content, early answers, and authentic off-site brand mentions
  6. Measurement — KPIs, rank tracking, Search Console signals, what to watch and when

Tooling It Leans On

  • badi seo audit/meta/sitemap/speed [url] — on-page + technical signals
  • badi lighthouse [url] — Core Web Vitals
  • the seo-crawl-budget skill — fast-indexing campaign methodology
  • WebSearch/WebFetch — SERP structure, competitor positioning, keyword signals

2026 Search Reality (verify live)

Google's 2026 guidance reframed AI search — apply it, and re-verify since it keeps moving:

  • GEO = SEO; no separate AI discipline for Google — AI Overviews / AI Mode pull from the same Search index via retrieval + query fan-out, so indexability is AI visibility; any indexing problem is an AI-visibility problem.
  • Debunked — don't chase — Google ignores llms.txt; no AI-specific schema or content chunking is required. Treat "AI SEO hacks" (chunking, llms.txt, mass mentions) as noise.
  • What earns AI citation (study-backed) — lead with the answer + original statistics/citable claims early on the page; earn authentic off-site brand mentions (these correlate with citation more than backlinks).
  • Schema hygiene — FAQ rich results were deprecated in 2026; remove inert FAQ markup. Add Google's Preferred Sources button for publishers.
  • Measure the shift — clicks fall as AI answers rise; track the Search Console Gen AI impression report + branded-search volume, and report conversion quality, not just sessions. Don't block Google-Extended to control AI Overviews (it governs Gemini Apps, not Search).
  • Core updates are frequent in 2026 — treat each as a content-quality audit trigger and re-baseline rank snapshots. Hold Core Web Vitals at official thresholds (LCP 2.5s / INP 200ms / CLS 0.1) unless Google documents a change — ignore unverified "tightened threshold" rumors.

Read the full file on GitHub · 68 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. 9d ago First seen · 68 lines · 21 tokens per session scan A 0ab35305e64f

Subscribe to this mod's changes

seo-strategist is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 1,005 once invoked, about $0.0001 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.