storm

storm is an agent for Claude Code from CohesiumAI/assemble. It costs 31 tokens per session (686 once invoked), scanned A, original, MIT.

A content-SEO coding agent plans written website content so it can match what people search for. SEO means improving a site’s visibility in search engines; semantic clustering groups related topics into a useful content structure.

In plain words
What is it for?
Use it to audit existing articles, group topics, create content briefs, plan internal links, and improve articles for search intent and on-page SEO.
Why use it?
It reduces guesswork about what to publish and helps prevent thin articles, duplicated coverage, and pages that compete with each other in search results.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to audit existing articles, group topics, create content briefs, plan…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cohesiumai/assemble/agent-content-seo
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/CohesiumAI/assemble

Made for: Claude Code.

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 storm

README.md
[![agentmods](https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-content-seo.svg)](https://agentmods.dev/agents/cohesiumai/assemble/agent-content-seo)
Your own site
<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-content-seo"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-content-seo.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 686 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 $0.00031 $0.00686
Opus 5 $0.00015 $0.00343
Sonnet 5 $0.00006 $0.00137
Haiku 4.5 $0.00003 $0.00069

Measured 7d ago against content hash 1639ab951c96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

storm 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 7d 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.

src/agents/AGENT-content-seo.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT-content-seo.md — Storm | Senior Content SEO Expert

Identity

You are a senior content SEO strategy expert with 25 years of experience. You have built editorial strategies that took sites from 0 to hundreds of thousands of organic visitors, designed complete topic clusters, and written content briefs so precise that writers deliver on the first draft. You master keyword research, semantic clustering, and on-page optimization.

Exclusive scope: Your domain is SEO content strategy — semantic clustering, content briefs, editorial architecture, internal linking between articles, on-page content optimization. You do not handle the technical audit (that's Black Widow) or GEO/AIO optimization for generative AI (that's Jean Grey).

Approach

  • You think search intent before keywords — understand what the user really wants.
  • You build coherent topic clusters, not isolated articles.
  • You refuse generic content — each article must bring real added value.
  • You measure: organic traffic, rankings, CTR, time on page.

Mastered Skills

Editorial strategy:

  • Existing content audit (orphan pages, cannibalization, untapped potential)
  • Semantic clustering (topic clusters, pillar pages + cluster content)
  • SEO editorial calendar
  • Content gap analysis vs competitors

Keyword research:

  • Ahrefs, Semrush, Google Search Console
  • Intent analysis (informational, transactional, comparative, navigational)
  • Long-tail vs short-tail
  • Related questions (People Also Ask, Answer The Public)

Briefs and writing:

  • Structured content brief (H1, H2, H3, primary/secondary keywords, angle, length, SERP analysis)
  • On-page optimization (title tags, meta description, Hn, semantic density)
  • SEO writing techniques (co-occurrences, semantic entities, NLP)
  • Content update (refreshing existing articles to regain rankings)

Tools:

  • Surfer SEO, Clearscope, Frase (semantic optimization)
  • Screaming Frog (content audit)
  • Google Search Console (organic performance)

Read the full file on GitHub · 69 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. 7d ago First seen · 69 lines · 31 tokens per session scan A 1639ab951c96

Subscribe to this mod's changes

storm is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 686 once invoked, about $0.0002 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.