content-twitter

content-twitter is a skill for Claude Code, Codex from vstorm-co/content-skills. It costs 37 tokens per session (1,226 once invoked), scanned A, original, MIT.

A writing guide for creating single posts and multi-post threads on X, formerly called Twitter, with a consistent brand voice and an attention-grabbing opening.

In plain words
What is it for?
Use it to draft tweets, X posts, and threads, including short announcements, questions, opinions, link commentary, stories, and step-by-step explanations.
Why use it?
It helps turn a topic, message, audience, link, or call to action into the right post format without losing the intended tone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to draft tweets, X posts, and threads, including short announcements, questions, opinions, link commentary, stories, and step-by-step explanations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vstorm-co/content-skills/content-twitter
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.

Any agent
npx skills add vstorm-co/content-skills --skill content-twitter
Clone the repo
git clone --depth 1 https://github.com/vstorm-co/content-skills

Made for: Claude Code, Codex.

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 content-twitter

README.md
[![agentmods](https://agentmods.dev/badge/skills/vstorm-co/content-skills/content-twitter/github.svg)](https://agentmods.dev/skills/vstorm-co/content-skills/content-twitter)
Your own site
<a href="https://agentmods.dev/skills/vstorm-co/content-skills/content-twitter"><img src="https://agentmods.dev/badge/skills/vstorm-co/content-skills/content-twitter/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.

agentmods 80×15 button for content-twitter

Your own site · 80×15
<a href="https://agentmods.dev/skills/vstorm-co/content-skills/content-twitter"><img src="https://agentmods.dev/badge/skills/vstorm-co/content-skills/content-twitter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,226 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 $0.00037 $0.01226
Opus 5 $0.00018 $0.00613
Sonnet 5 $0.00007 $0.00245
Haiku 4.5 $0.00004 $0.00123

Measured 10d ago against content hash 7e9bc87a0f1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

content-twitter 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 10d 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.

skills/content-twitter/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

X/Twitter Content Generation

Before You Start

  1. Check for brand voice: Read brand/VOICE.md if it exists. Adapt the brand voice for X's more informal, direct tone. If no voice file exists, default to conversational, direct, and personality-forward.

  2. Determine content format: Decide between a single tweet and a thread based on the content.

  3. Gather inputs: Topic, key message, target audience, any links or media to include, desired CTA.


Thread vs. Single Tweet Decision

Use a single tweet when:

  • The idea fits in one punch (under 280 characters)
  • You are sharing a link with commentary
  • You are making a bold claim or hot take
  • You are asking a question

Use a thread when:

  • The topic requires explanation or multiple steps
  • You are telling a story
  • You are breaking down a complex idea
  • You want to maximize engagement through a multi-part narrative

Hook-First Writing

The first tweet (whether standalone or the start of a thread) must stop the scroll. It is the most important piece of content you write.

Rules for hooks:

  • Lead with the most interesting, surprising, or valuable part of your content
  • Never open with context or background. Start with the payoff, then backfill.
  • The hook must work without the reader knowing anything about you or your topic
  • If your hook starts with "So," "Just," or "I think," rewrite it

Reference hook-patterns.md for proven hook formulas with examples.


Thread Structure

Every thread follows this three-act structure:

Act 1: Hook (Tweet 1)

  • Stop the scroll
  • Create a curiosity gap or deliver an immediate value promise
  • Include a signal that a thread is coming ("A thread:" or the /thread emoji or a numbered "1/")

Act 2: Value (Tweets 2 through N-1)

  • Each tweet must stand alone as a valuable insight, even out of context
  • Number your tweets for easy reference and readability
  • Keep each tweet focused on one point
  • Use line breaks within tweets for readability
  • Include specifics: data, examples, names, numbers
  • Vary tweet length: some punchy (1-2 lines), some fuller (3-4 lines)

Read the full file on GitHub · 140 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 140 lines · 37 tokens per session scan A 7e9bc87a0f1d

Subscribe to this mod's changes

content-twitter is a skill published in the GitHub repository vstorm-co/content-skills (22 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 1,226 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.