draft-content

draft-content is a command for coding agents from fergupa/claude_plugins. It costs 19 tokens per session (941 once invoked), scanned A, original, Apache-2.0.

A tool for drafting marketing materials, including blog posts, social posts, newsletters, landing pages, press releases, and case studies.

In plain words
What is it for?
Use it when you need first drafts for campaigns, websites, email newsletters, public announcements, or customer stories.
Why use it?
It gives you a starting draft tailored to the content type, audience, key messages, tone, and length.

Command

Part of the marketing plugin — 5 skills, 7 commands shipped together

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/fergupa/claude_plugins/draft-content
Clone the repo
git clone --depth 1 https://github.com/fergupa/claude_plugins

Or install marketing, the plugin that ships this one along with the rest of its 5 skills, 7 commands.

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 draft-content

README.md
[![agentmods](https://agentmods.dev/badge/commands/fergupa/claude_plugins/draft-content.svg)](https://agentmods.dev/commands/fergupa/claude_plugins/draft-content)
Your own site
<a href="https://agentmods.dev/commands/fergupa/claude_plugins/draft-content"><img src="https://agentmods.dev/badge/commands/fergupa/claude_plugins/draft-content.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 941 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 $0.00019 $0.00941
Opus 5 $0.00010 $0.00470
Sonnet 5 $0.00004 $0.00188
Haiku 4.5 $0.00002 $0.00094

Measured yesterday against content hash 3cd48c55708c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft-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 yesterday.

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.

marketing/commands/draft-content.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft Content

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Generate marketing content drafts tailored to a specific content type, audience, and brand voice.

Trigger

User runs /draft-content or asks to draft, write, or create marketing content.

Inputs

Gather the following from the user. If not provided, ask before proceeding:

  1. Content type — one of:

    • Blog post
    • Social media post (specify platform: LinkedIn, Twitter/X, Instagram, Facebook)
    • Email newsletter
    • Landing page copy
    • Press release
    • Case study
  2. Topic — the subject or theme of the content

  3. Target audience — who this content is for (role, industry, seniority, pain points)

  4. Key messages — 2-4 main points or takeaways to communicate

  5. Tone — e.g., authoritative, conversational, inspirational, technical, witty (optional if brand voice is configured)

  6. Length — target word count or format constraint (e.g., "1000 words", "280 characters", "3 paragraphs")

Brand Voice

  • If the user has a brand voice configured in their local settings file, apply it automatically. Inform the user that brand voice settings are being applied.
  • If no brand voice is configured, ask: "Do you have brand voice guidelines you'd like me to follow? If not, I'll use a neutral professional tone."
  • Apply the specified or default tone consistently throughout the draft.

Content Generation by Type

Blog Post

  • Engaging headline (provide 2-3 options)
  • Introduction with a hook (question, statistic, bold statement, or story)
  • 3-5 organized sections with descriptive subheadings
  • Supporting points, examples, or data references in each section
  • Conclusion with a clear call to action
  • SEO considerations: suggest a primary keyword, include it in the headline and first paragraph, use related keywords in subheadings

Social Media Post

  • Platform-appropriate format and length
  • Hook in the first line
  • Hashtag suggestions (3-5 relevant hashtags)
  • Call to action or engagement prompt
  • Emoji usage appropriate to brand and platform
  • If LinkedIn: professional framing, paragraph breaks for readability
  • If Twitter/X: concise, punchy, within character limit
  • If Instagram: visual-first language, story-driven, hashtag block

Read the full file on GitHub · 117 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. yesterday First seen · 117 lines · 19 tokens per session scan A 3cd48c55708c

Subscribe to this mod's changes

draft-content is a command published in the GitHub repository fergupa/claude_plugins (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 941 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 2026-09-03.