write

write is a command for Claude Code from TheCraigHewitt/seomachine. It costs 0 tokens per session (3,983 once invoked), scanned A, original, MIT.

A command for creating long, search-friendly blog articles from a topic or research brief. It follows project materials such as brand voice, writing examples, style rules, keywords, and linking guidance.

In plain words
What is it for?
Use it to draft complete blog posts, including a headline, introduction, article structure, internal and external links, and search-engine metadata.
Why use it?
It brings research, tone, structure, search terms, links, and publishing metadata into one writing workflow.

Command for Claude Code

About the project

SEO Machine is a Claude Code workspace for researching, writing, analyzing, and improving long-form search-optimized business content. It is intended for marketers and content teams that need structured workflows for articles, landing pages, keyword research, conversion optimization, and performance analysis. Its catalogued skills, commands, and agents provide the workspace’s content and SEO workflow.

TheCraigHewitt/seomachine · 7,399 stars · on GitHub

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 commands/thecraighewitt/seomachine/write
Clone the repo
git clone --depth 1 https://github.com/TheCraigHewitt/seomachine

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 write

README.md
[![agentmods](https://agentmods.dev/badge/commands/thecraighewitt/seomachine/write.svg)](https://agentmods.dev/commands/thecraighewitt/seomachine/write)
Your own site
<a href="https://agentmods.dev/commands/thecraighewitt/seomachine/write"><img src="https://agentmods.dev/badge/commands/thecraighewitt/seomachine/write.svg" alt="Measured on agentmods" height="20"></a>
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 3,983 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 $0.03983
Opus 5 $0.00000 $0.01992
Sonnet 5 $0.00000 $0.00797
Haiku 4.5 $0.00000 $0.00398

Measured 5d ago against content hash b99c5247128f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write 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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • write — 92% identical, 50 lines differ
.claude/commands/write.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Command

Use this command to create comprehensive, SEO-optimized long-form blog content.

Usage

/write [topic or research brief]

What This Command Does

  1. Creates complete, well-structured long-form articles (2000-3000+ words)
  2. Optimizes content for target keywords and SEO best practices
  3. Maintains your brand voice and messaging throughout
  4. Integrates internal and external links strategically
  5. Includes all meta elements for publishing

Process

Pre-Writing Review

  • Research Brief: Review research brief from /research command if available
  • Brand Voice: Check @context/brand-voice.md for tone and messaging
  • Writing Examples: Study @context/writing-examples.md for style consistency
  • Style Guide: Follow formatting rules from @context/style-guide.md
  • SEO Guidelines: Apply requirements from @context/seo-guidelines.md
  • Target Keywords: Integrate keywords from @context/target-keywords.md naturally

Content Structure

1. Headline (H1)
  • Include primary keyword naturally
  • Create compelling, click-worthy title
  • Keep under 60 characters for SERP display
  • Promise clear value to reader
2. Introduction (150-250 words)

CRITICAL: Direct Answer First (AI Search Optimization)

For any "best/top/how" query, the first 1-2 sentences MUST directly answer the question. AI scrapers (ChatGPT, Perplexity, Gemini) pull from the top of the page. Don't bury the answer behind narrative.

Example — "best project management tools":

The best project management tools in 2026 are Asana, Monday, and ClickUp — each built for different team sizes and workflows. Here's how they compare.

After the direct answer, use a hook to keep human readers engaged.

Choose ONE hook type for each article:

Hook Type Example Best For
Provocative Question "What if the 'free' plan is actually costing you $500/month in lost opportunities?" Challenging assumptions
Specific Scenario "Last Tuesday, Sarah checked her dashboard and discovered something alarming: her site had been invisible to Google for three weeks." Creating emotional connection
Surprising Statistic "73% of SaaS users who switch platforms do so within 18 months, and most cite the same three reasons." Data-driven topics
Bold Statement "Your current tool is lying to you about your numbers." Controversial takes
Counterintuitive Claim "The cheapest option might be the most expensive decision you make this year." Comparison content

Read the full file on GitHub · 391 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. 5d ago First seen · 391 lines · 0 tokens per session scan A b99c5247128f

Subscribe to this mod's changes

write is a command published in the GitHub repository TheCraigHewitt/seomachine (7,399 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,983 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 2026-08-30.