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 oegeyilmaz9/seo-aeo-geo-ultimate/plugin install seo-aeo-geo-ultimateWrote 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/skills/oegeyilmaz9/seo-aeo-geo-ultimate/seo)<a href="https://agentmods.dev/skills/oegeyilmaz9/seo-aeo-geo-ultimate/seo"><img src="https://agentmods.dev/badge/skills/oegeyilmaz9/seo-aeo-geo-ultimate/seo/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/skills/oegeyilmaz9/seo-aeo-geo-ultimate/seo"><img src="https://agentmods.dev/badge/skills/oegeyilmaz9/seo-aeo-geo-ultimate/seo.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 | $0.00087 | $0.02831 |
| Opus 5 | $0.00044 | $0.01416 |
| Sonnet 5 | $0.00017 | $0.00566 |
| Haiku 4.5 | $0.00009 | $0.00283 |
Grade A, and why
seo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Router
Use seo as the default front door and user-facing owner for every request in this suite: a narrow technical question, a content review, an AI-search investigation, a multi-team plan, or an end-to-end authorized change. The user states the outcome in ordinary language; the router screens all 27 skills, executes every applicable specialist workflow, carries intermediate evidence and decisions internally, and returns one consolidated result. It does not ask the user to coordinate the suite, duplicate specialist logic, invent findings, or merge unlike metrics into one score.
Read autonomous-orchestration-contract.md for every request before selecting or executing specialist lanes. Read routing-matrix.md before routing a request through the suite. Read decision-and-release-contract.md when the requested work can continue from evidence into implementation, release, provider mutation, or delayed outcome follow-up.
User burden boundary
- Never require the user to know whether their problem is SEO, AEO, GEO, AI-search, technical, content, authority, or measurement.
- Never ask the user to choose a specialist, artifact, schema, validator, or phase order. Infer and manage those internally.
- Ask only for material business truth, inaccessible data/access, an outcome-changing choice, cost-bearing action, or authorization that cannot be safely inferred.
- A direct specialist call remains supported for expert users, but it is never a prerequisite for complete work through
seo.
Routing procedure
- Translate the user's ordinary-language goal into the requested outcome and authorized boundary: answer, research, audit, decision, strategy, measurement, implementation, release verification, provider operation, follow-up, or end-to-end completion.
- Inspect available site/repository/data context before asking questions. Infer the surface, locale, verticals, technical system, and affected scope; ask only for non-discoverable material facts or permissions.
- Create the 27-skill coverage ledger from the autonomous orchestration contract. Mark every capability
required,active,completed,not-applicable,blocked, ordeferred-by-ownerwith evidence or a reason. A broad request cannot skip the screen; a narrow request still receives the screen internally. - Build the dependency graph and load each required specialist's full
SKILL.mdbefore executing that lane. The router—not the user—invokes or performs the next specialist workflow and transfers its evidence/artifacts. - For a broad request to rank higher, improve organic visibility, or optimize a site/page, establish the intended query families with
seo-research, review the page's search-result presentation withseo-pageandseo-content, and verify hostname-level favicon/site identity withseo-technical. Require two concurrent opportunity tracks: evidence-backed nearer-term gains and high-volume head-term/category leadership. Preserve every owner-declared relevant high-volume family as a required strategic target; current difficulty or an authority gap changes the work and sequence, not whether the target is analyzed. Do not let a broad closeout omit title, descriptive meta description, favicon, canonical/indexability, or query-to-page ownership merely because each item is individually simple. Do not let easier work replace or hide the head-term leadership track. A deliberately narrow request remains narrow. - For compound optimize-and-track work, use this phase order:
research -> audit -> baseline measurement -> product-owner decision -> action planning -> authorized implementation -> local acceptance -> authorized release -> live delivery verification -> authorized provider operation -> delayed outcome follow-up. - Require each phase's real artifact or explicit limitation before starting a dependent phase. AEO/GEO work hands off a validated
optimization-brief.json; conventional SEO lanes hand off a validatedseo-findings.jsonbundle. Reuse an existing goal, issue, or Action Plan when it already records the full decision; otherwise add the short decision record defined in the decision-and-release contract. Do not let a downstream specialist silently repair missing upstream evidence or self-approve a change. - Continue through every safe read-only/local and explicitly authorized phase while useful work remains. Evaluate authorization separately for implementation, release, and provider mutation. When later authorization arrives, resume the same decision and candidate chain rather than restarting or substituting work.
- Parallelize only independent lanes when the runtime permits it. Keep the final synthesis with the router, preserve disagreements instead of averaging them away, and do not expose intermediate handoff work as user homework.
- Close critical and important findings before release; record minor findings in backlog. Review one candidate hash at most twice. Finish with one consolidated outcome and, for broad work, a compact 27-skill coverage summary.
What ships with it
16 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.
- agents/openai.yaml 427 B
- references/autonomous-orchestration-contract.md 9.4 KB
- references/contracts/action-plan.schema.json 10 KB
- references/contracts/contracts-lock.json 5.4 KB
- references/contracts/evidence-record.schema.json 1.7 KB
- references/contracts/optimization-brief.schema.json 6.3 KB
- references/contracts/platform-controls.schema.json 6.6 KB
- references/contracts/provider-operation-receipt.schema.json 6.5 KB
- references/contracts/query-corpus.schema.json 6.0 KB
- references/contracts/research-pack.schema.json 5.2 KB
- references/contracts/seo-findings.schema.json 5.2 KB
- references/contracts/seo-performance-run.schema.json 7.6 KB
- references/contracts/site-graph.schema.json 4.3 KB
- references/contracts/visibility-run.schema.json 14 KB
- references/decision-and-release-contract.md 2.6 KB
- references/routing-matrix.md 9.3 KB
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 · 93 lines · 87 tokens per session scan A b8621a657a09
seo is a skill published in the GitHub repository oegeyilmaz9/seo-aeo-geo-ultimate (2 stars, last pushed 23d ago), licensed Apache-2.0. It adds 87 tokens to every session and 2,831 once invoked, about $0.0004 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.
Other skills, from other repositories
ansvisor-aeo-coach-standalone
Standalone (no-MCP) version of the Ansvisor AEO Coach. Use this only when the user's Claude client cannot connect to the Ansvisor MCP server (e.g. claude.ai web without a Connector configured). Fetches live data from the Ansvisor REST API directly with the user's API key via code execution. For clients that support…
seo-vertical-detect
Classify a website as ecommerce, local-business, blog-publisher, saas, docs, or generic (multiple may apply), and report detected locales, from the persisted PageSnapshot plus the platform detector's vertical hints. Used by seo-orchestrator to decide which conditional modules to run and how to reweight the scores.
ansvisor-aeo-coach
Acts as an Answer Engine Optimization (AEO) analyst for users running Ansvisor. Activates when the user asks how their brand is doing across AI search engines (ChatGPT, Gemini, Perplexity, Claude, Copilot, AI Overview, AI Mode), why visibility changed, or how they compare to competitors. Uses the Ansvisor MCP server…
seo-fix-apply
Writer protocol preloaded into the seo-fixer-writer agent — how confirmed SEO/AI-search fixes are applied (git pre-flight, backup, Edit/Write for local diffs, ticketed adapter CLIs for remote targets, re-verify, publish only on a second ticket, rollback) and the findings-array output contract. Used only by the fix…
audit
Audit a website or web codebase for SEO and AI-search (GEO/AEO) — produces two independent 0-100 scores (Search SEO + AI Visibility) plus a prioritized, evidence-backed report persisted on disk. Read-only; never writes to the project. Use when the user asks to audit, analyze, check, or score a site's SEO, structured…
orangeo-ai-visibility-skill
Audit brand AI visibility readiness and prepare OranGEO-style GEO, AEO, LLM SEO, and AI search optimization action plans. Use when asked for a Claude Code skill, Codex skill, GEO skill, generative engine optimization skill, answer engine optimization skill, AI visibility audit, AI search visibility checker, llms.txt…