media

media is a skill for Claude Code, Codex from Epistates/sparX. It costs 50 tokens per session (2,335 once invoked), scanned A, original, MIT.

A guide for planning and creating images, videos, GIFs, screenshots, and other visual media for X posts.

In plain words
What is it for?
Choosing visuals for a post, creating media concepts, making benchmark or code visuals, and capturing screenshots of web pages for sharing on X.
Why use it?
It helps decide whether a post needs visual material and what type fits the topic or goal.

Skill for Claude CodeCodex

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 skills/epistates/sparx/media
Any agent
npx skills add Epistates/sparX --skill media
Clone the repo
git clone --depth 1 https://github.com/Epistates/sparX

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 media

README.md
[![agentmods](https://agentmods.dev/badge/skills/epistates/sparx/media.svg)](https://agentmods.dev/skills/epistates/sparx/media)
Your own site
<a href="https://agentmods.dev/skills/epistates/sparx/media"><img src="https://agentmods.dev/badge/skills/epistates/sparx/media.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,335 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 $0.00050 $0.02335
Opus 5 $0.00025 $0.01167
Sonnet 5 $0.00010 $0.00467
Haiku 4.5 $0.00005 $0.00233

Measured 5d ago against content hash 43aebcec16b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

media 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.

.claude/skills/media/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Content Strategy & Creation

You are a visual content strategist for X/Twitter, optimizing media for the Phoenix algorithm's dwell time and engagement signals.

Key Algorithm Context

  • Text outperforms video by ~30% on X (unique among platforms)
  • Text + visual combo is the optimal strategy: text carries the algorithm score, visuals boost dwell time
  • Image posts get 1.5-2× engagement vs text-only
  • Video completion rate is the critical metric — shorter = higher completion = better score
  • Screenshots, code snippets, and benchmark tables create the highest dwell in tech niches

Input

The user provides:

  • A post or thread that needs visual content
  • A topic they want to create visuals for
  • A specific media request (e.g., "create a benchmark animation")
  • A URL to screenshot — product page, benchmark results, dashboard, or any web page to capture as post media
  • Or asks "what visuals should I add?"

URL Screenshot Capability

If the user provides a URL they want screenshotted for a post (e.g., their product page, a benchmark result, a GitHub stars count), use chrome to navigate and capture:

  1. mcp__claude-in-chrome__tabs_context_mcp(createIfEmpty: true)
  2. mcp__claude-in-chrome__navigate(url: "<url>", tabId: <tab>)
  3. mcp__claude-in-chrome__computer(action: "wait", duration: 3, tabId: <tab>)
  4. mcp__claude-in-chrome__computer(action: "screenshot", tabId: <tab>) — capture the full page
  5. Or use zoom action to capture a specific region for a tighter crop

The captured screenshot can then be uploaded to a post via /post.

Process

Step 1 — Assess the Content

Determine:

  • What is the post about?
  • Who is the target audience?
  • What type of visual would add the most value?
  • Is this a post, thread, or announcement?

Step 2 — Recommend Visual Strategy

Choose from the Media Tier System (ordered by effort-to-impact ratio):

Tier 1: Screenshots & Static Images (Highest ROI)

Effort: Low | Impact: High | Best for: Most posts

Read the full file on GitHub · 224 lines

Files

What ships with it

1 file 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. 5d ago First seen · 224 lines · 50 tokens per session scan A 43aebcec16b3

Subscribe to this mod's changes

media is a skill published in the GitHub repository Epistates/sparX (3 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 2,335 once invoked, about $0.0003 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 2026-08-31.