media-gen

media-gen is a skill for Claude Code from ManceRayder42/jarvis-os. It costs 216 tokens per session (2,206 once invoked), scanned A, original, MIT.

An image and video creation tool that sends requests to current models through fal.ai, a pay-per-use service for generative media. It can also upscale images and turn images into video.

In plain words
What is it for?
Use it for website hero images, short video loops, image-to-video clips, photorealistic visuals, and image upscaling.
Why use it?
It gives one place to create or improve visual media while charging each request against prepaid credits. The usage rules help limit video costs.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: positional $N argument.

Part of the jarvis-os plugin — 16 skills, 1 command shipped together

Good fit Use it for website hero images, short video loops, image-to-video clips, photorealistic visuals, and image upscaling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mancerayder42/jarvis-os/media-gen
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 ManceRayder42/jarvis-os --skill media-gen
Clone the repo
git clone --depth 1 https://github.com/ManceRayder42/jarvis-os

Made for: Claude Code.

Or install jarvis-os, the plugin that ships this one along with the rest of its 16 skills, 1 command.

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-gen

README.md
[![agentmods](https://agentmods.dev/badge/skills/mancerayder42/jarvis-os/media-gen/github.svg)](https://agentmods.dev/skills/mancerayder42/jarvis-os/media-gen)
Your own site
<a href="https://agentmods.dev/skills/mancerayder42/jarvis-os/media-gen"><img src="https://agentmods.dev/badge/skills/mancerayder42/jarvis-os/media-gen/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 media-gen

Your own site · 80×15
<a href="https://agentmods.dev/skills/mancerayder42/jarvis-os/media-gen"><img src="https://agentmods.dev/badge/skills/mancerayder42/jarvis-os/media-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 216 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,206 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00216 $0.02206
Opus 5 $0.00108 $0.01103
Sonnet 5 $0.00043 $0.00441
Haiku 4.5 $0.00022 $0.00221

Measured 11d ago against content hash d336677acb51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

media-gen scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST "https://fal.run/<model-slug>" \
skills/media-gen/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

media-gen — fal.ai cost-router

One fal.ai key covers every current image/video model, pay-per-use — no subscription, no monthly minimum. You prepay credit on fal.ai's dashboard and each request draws down from it: spend is real money — be surgical.

Auth

Read the key from the environment first; fall back to the hub's .env (the /jarvis-setup page's Media section writes it there). The hub itself resolves the same way the SessionStart hook does: JARVIS_HUB env var first, else the pointer file at ~/.jarvis-hub-path written by /jarvis-setup, else ~/jarvis-hub. Never hardcode a path to it and never echo/print/log the value:

hub="${JARVIS_HUB:-$(cat ~/.jarvis-hub-path 2>/dev/null)}"
hub="${hub:-$HOME/jarvis-hub}"
FAL_KEY="${FAL_KEY:-$(grep '^FAL_KEY=' "$hub/.env" 2>/dev/null | cut -d= -f2-)}"

If FAL_KEY is still empty after that, stop and tell the user to add it via /jarvis-setup — do not hunt for it elsewhere. Every request: header Authorization: Key $FAL_KEY.

Cost discipline (the point of this skill)

  • Images are cheap (fractions of a cent). Iterate freely.
  • Video bills per second. Default 3–5s, never more without an explicit ask. 5s vs 10s = real dollars. State the model + estimated cost BEFORE a video run and get the user's go-ahead unless they already gave one this session.
  • Cheapest-fit routing: draft/test → FLUX schnell; final image → FLUX dev or nano-banana Pro; image→video → Kling (best value) before Seedance (pricier); upscale → Topaz only when the target actually needs it.
  • No balance API — track spend at https://fal.ai/dashboard (billing page).

Model routing

Models rotate fast; slugs below verified 2026-07-14. When one 404s or a newer generation is out, search https://fal.ai/models?q= (WebFetch) — new models work with the same key + call shape, no skill change.

Need Model slug Notes
Draft/test image fal-ai/flux/schnell ~free, 1-4 steps
Final image fal-ai/flux/dev quality tier
Photoreal/edit image fal-ai/nano-banana-pro Gemini-family
Image → video fal-ai/kling-video/v3/standard/image-to-video best cheap; try v-latest
Image → video (premium) fal-ai/bytedance/seedance (latest pro) pricier, smoother camera
Two frames → video (interpolate) fal-ai/wan-flf2v (start_image_url/end_image_url) cheapest FLF2V, $0.2/video @480p, $0.4 @720p (verified 2026-08-19). Mid-tier fal-ai/kling-video/o1/standard/image-to-video ($0.084/s, same param names, end_image_url optional). Premium fal-ai/veo3.1/first-last-frame-to-video ($0.20/s, different param names: first_frame_url/last_frame_url, generate_audio defaults true — turn it off)
Upscale image fal-ai/topaz/upscale only on real need

Read the full file on GitHub · 153 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. 11d ago First seen · 153 lines · 216 tokens per session scan A d336677acb51

Subscribe to this mod's changes

media-gen is a skill published in the GitHub repository ManceRayder42/jarvis-os (5 stars, last pushed 6d ago), licensed MIT. It adds 216 tokens to every session and 2,206 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

repurpose-talk

Use when the user just gave a talk, panel, fireside chat, keynote, workshop, podcast, or webinar and wants content made from it — triggers like "I just gave a talk", "the panel is done", "just finished speaking", "turn my talk into LinkedIn posts", "repurpose this recording/transcript into posts, notes, or clips", or…

mycelium-hq/ai-brain-starter · 101 tokens

dream

Deep creative exploration engine. Competing perspectives, stress-tested by a 4-persona council, scored by integrity. The approach that survives attack wins — not the one that sounds best.

ariaxhan/kernel-claude · 39 tokens

cinematic-hero

The house style for CINEMATIC MOTION + STILLS — best-in-the-world animated hero GIFs/MP4s and cinematic stills (deck covers, social cards, launch visuals), in one signature look. Triggers on requests for a "hero GIF/video", "cinematic" anything, "animated logo/wordmark", "launch/hero/demo asset", "motion graphic"…

Rishi4792/compass · 203 tokens

canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

composio-community/awesome-claude-plugins · 59 tokens

confidence-gate

When you're about to claim success ("fixed", "done", "works", "passing tests") at the end of a turn, verify the claim is backed by actual evidence in this session. presence's Stop hook will flag a success claim that has no recent test/build pass behind it. Be aware of this gate and either run the verification, or…

sara-star-quant/presence · 78 tokens

artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

composio-community/awesome-claude-plugins · 63 tokens