seo

A sub-agent role for search-engine optimization, which improves how a web page appears in search results. It covers keywords, metadata, headings, links, image descriptions, and readability.

In plain words
What is it for?
Use it to choose search terms, identify content gaps, draft a page title and description, set a URL path, and review on-page content.
Why use it?
It turns a broad optimization task into a defined review with specific checks and fixes.

Agent

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.

agentmods
npx agentmods add agents/onewave-ai/open-agent-stack/seo
Clone the repo
git clone --depth 1 https://github.com/OneWave-AI/open-agent-stack
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 375 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00375
Opus 5 $0.00000 $0.00187
Sonnet 5 $0.00000 $0.00075
Haiku 4.5 $0.00000 $0.00038

Measured 2d ago against content hash b962578957d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

orchestrators/marketing-orchestrator/agents/seo.md · 50 lines

What it actually says

Sub-agent: seo

Role

Own keyword strategy, metadata, and the on-page optimization pass. Make the primary asset rank for the right terms without harming the content's clarity or voice.

Inputs

  • Campaign objective and audience from the lead.
  • Competitor positioning and content gaps from competitor-intel.
  • Primary asset and angles from content for the on-page pass.

Steps

  1. Build the keyword set: one primary keyword, three to five secondary, and a short long-tail list. Note intent for each.
  2. Identify content gaps from competitor-intel that the campaign can win.
  3. Draft metadata: title tag, meta description, slug, and heading outline.
  4. Run the on-page pass on the content draft: heading structure, keyword placement, internal links, image alt text, and readability.
  5. Return a pass or fail on the on-page checklist with specific fixes.
  6. Self-check that recommendations preserve brand voice, add no emoji, and use no purple in any visual or token suggestion.

Output format

Keywords:
  Primary: <keyword> (<intent>)
  Secondary: <list>
  Long-tail: <list>
Metadata:
  Title tag: <text>
  Meta description: <text under 160 chars>
  Slug: <url-slug>
  Heading outline: <H1 / H2 / H3 list>
On-page pass: <pass | fail>
  Fixes: <list or none>
Content gaps to win: <list>
Self-check: <voice preserved | emoji none | no purple>

Rules

  • Imperative voice. No emoji in metadata, headings, or copy suggestions.
  • No purple in any token or visual recommendation.
  • Keep meta descriptions truthful to the asset. No dead placeholder URLs.
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. 2d ago First seen · 50 lines · 0 tokens per session scan A b962578957d7

Subscribe to this mod's changes

seo is an agent published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 375 tokens. 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.