write

A command for turning a topic or research brief into a complete long-form article. It covers structure, evidence, examples, voice, and supporting context.

In plain words
What is it for?
Use it to create articles for publication, integrate research and examples, maintain a consistent writing style, and produce a master draft that can later be adapted for other platforms.
Why use it?
A large amount of research or scattered material still needs a coherent narrative before it can be published. The command organises that material into a readable draft with an introduction and conclusion.

Command for Claude Code

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/womendefiningai/claudecode-writer/write
Clone the repo
git clone --depth 1 https://github.com/WomenDefiningAI/claudecode-writer

Made for: Claude Code.

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 673 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 $0.00673
Opus 5 $0.00000 $0.00336
Sonnet 5 $0.00000 $0.00135
Haiku 4.5 $0.00000 $0.00067

Measured 2d ago against content hash b2a1ab4a18a1, 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 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.

.claude/commands/write.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 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 long-form articles.

Usage

/write [topic or research brief]

What This Command Does

  1. Creates a complete, well-structured article
  2. Ensures consistent voice and style throughout
  3. Includes compelling introduction and conclusion
  4. Integrates supporting examples and data
  5. Optimizes for readability and engagement

Process

  • Research Integration: Weave in current trends, fresh data, and timely examples
  • Competitive Context: Reference (and improve on) existing perspectives
  • Structure with Surprise: Build article flow that challenges conventional wisdom
  • Evidence Integration: Include recent studies, expert insights, real-world examples
  • Voice Authenticity: Ensure your unique perspective comes through clearly
  • Future-Forward: Connect current insights to emerging trends or implications

References

Always check @context/writing-examples.md for voice and style consistency.

Output

Provides a complete article ready for:

  • Direct publication
  • Repurposing by specialized agents
  • Further editing and refinement

The article should serve as the master content from which all platform-specific versions are derived.

File Management

After completing the article, automatically save the draft to:

  • File Location: drafts/article-[topic-slug]-[YYYY-MM-DD].md
  • File Format: Markdown with title, headers, and formatted content
  • Naming Convention: Use lowercase, hyphenated topic slug and current date

Example: drafts/article-remote-work-productivity-2024-01-15.md

This ensures all article drafts are systematically organized and available for future reference, editing, or repurposing.

Automatic Multi-Platform Repurposing

After saving the main article, immediately execute all platform-specific agents to create optimized versions:

1. LinkedIn Agent Execution

  • Agent: linkedin-repurposer
  • Input: Full article content
  • Output File: drafts/linkedin-[topic-slug]-[YYYY-MM-DD].md
  • Purpose: Professional networking post with engagement hooks

Read the full file on GitHub · 71 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. 2d ago First seen · 71 lines · 0 tokens per session scan A b2a1ab4a18a1

Subscribe to this mod's changes

write is a command published in the GitHub repository WomenDefiningAI/claudecode-writer (221 stars, last pushed 12mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 673 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.