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.
npx agentmods add skills/epistates/sparx/medianpx skills add Epistates/sparX --skill mediagit clone --depth 1 https://github.com/Epistates/sparXWrote 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.
[](https://agentmods.dev/skills/epistates/sparx/media)<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>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.
| Model | Per session | Once 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 |
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.
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:
mcp__claude-in-chrome__tabs_context_mcp(createIfEmpty: true)mcp__claude-in-chrome__navigate(url: "<url>", tabId: <tab>)mcp__claude-in-chrome__computer(action: "wait", duration: 3, tabId: <tab>)mcp__claude-in-chrome__computer(action: "screenshot", tabId: <tab>)— capture the full page- Or use
zoomaction 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
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.
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.
- 5d ago First seen · 224 lines · 50 tokens per session scan A 43aebcec16b3
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.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
golden-chat
Use when testing the goldenchat golden build.
golden-epub
Use when testing the epub golden build.
golden-epub-kw
Use when testing keyword categorization.
golden-html-multi
Use when testing the multi-file html build.
golden-jupyter
Use when testing the goldenjupyter golden build.