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/akii-technologies-ltd/akii-seo-ai-search-optimizerWrote 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/commands/akii-technologies-ltd/akii-seo-ai-search-optimizer/create-content)<a href="https://agentmods.dev/commands/akii-technologies-ltd/akii-seo-ai-search-optimizer/create-content"><img src="https://agentmods.dev/badge/commands/akii-technologies-ltd/akii-seo-ai-search-optimizer/create-content/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/commands/akii-technologies-ltd/akii-seo-ai-search-optimizer/create-content"><img src="https://agentmods.dev/badge/commands/akii-technologies-ltd/akii-seo-ai-search-optimizer/create-content.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 | $0.00015 | $0.00758 |
| Opus 5 | $0.00008 | $0.00379 |
| Sonnet 5 | $0.00003 | $0.00152 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
create-content 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 11d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create SEO + AEO + GEO Content
You are generating content powered by Akii.
Arguments
$ARGUMENTS contains the user's input. Parse:
- First word(s) up to first flag/dash: the topic (required)
- Type:
blog(default),guide,listicle,comparison,how-to,glossary— passed inline or as--type=... - Words: target length, default
1500— inline number or--words=... - Tone:
professional(default),casual,technical,friendly— inline or--tone=...
If anything is ambiguous, infer the most sensible default and proceed.
Steps
- Research —
WebSearchSERP top 10 for the topic; pull common entities, headings, PAA. Ifmcp__plugin_marketing_ahrefs__keywords-explorer-overviewavailable, fetch real volume + KD + parent topic. - Metadata — title (50–60 chars), meta (150–160 chars), URL slug.
- Structure — H1, H2/H3 outline, FAQ block.
- Write — full article body honoring brand voice + tone arg.
- Apply AEO — direct-answer lead ≤40 words, autonomous sections, definition blocks, 5–7 step imperative checklists.
- Apply GEO — auto-classify content domain → apply matching Princeton tactic (citations / quotes / stats / fluency / authoritative).
- SEO niceties — natural keyword use (NO stuffing — Princeton GEO study shows it cuts AI visibility ~10%), internal link placeholders, external citations to authoritative sources, image alt suggestions.
- Schema — emit appropriate JSON-LD (Article + FAQPage typically) inline.
Output
---
title: "<title>"
description: "<meta>"
slug: "<slug>"
keywords: ["primary","secondary","tertiary"]
schema: "Article" | "HowTo" | "FAQPage"
---
# <H1>
<direct-answer lead paragraph, ≤40 words>
<full article body — modular sections, definition blocks, lists>
## FAQ
### <Q1>?
<A1>
---
## SEO + AEO + GEO metadata
**Title**: ...
**Meta**: ...
**Primary keyword**: ...
**AEO score (est)**: 84
**GEO tactic applied**: <tactic>
**Internal links suggested**: [INTERNAL LINK: /path "anchor"] × N
**External citations**: N (gov/edu/major publications)
## Schema (JSON-LD)
```json
{...}
Image suggestions
- Hero:
- :
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.
- 11d ago First seen · 81 lines · 15 tokens per session scan A 1809c8dae501
create-content is a command published in the GitHub repository akii-technologies-ltd/akii-seo-ai-search-optimizer (76 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 758 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 2026-08-30.
Other commands, from other repositories
status
Show organic-os site status - pending approvals, recent signals, next routine.
sites
Manage organic-os sites - add another website, switch the active site, or show registry status.
reset
Guided teardown of an organic-os site - what gets deregistered automatically, what you must delete or revoke yourself, and why.
apply
Execute approved on-page proposals against WordPress (refuses anything not approved).
citations
Track AI answer-engine citations and share of voice for the profile's query set.
competitors
Run competitor content intelligence and surface gaps against the profile.