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 skills add rampstackco/claude-skills --skill media-asset-managementgit clone --depth 1 https://github.com/rampstackco/claude-skillsWrote 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/rampstackco/claude-skills/media-asset-management)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/media-asset-management"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/media-asset-management/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.
<a href="https://agentmods.dev/skills/rampstackco/claude-skills/media-asset-management"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/media-asset-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00111 | $0.02722 |
| Opus 5 | $0.00056 | $0.01361 |
| Sonnet 5 | $0.00022 | $0.00544 |
| Haiku 4.5 | $0.00011 | $0.00272 |
Grade A, and why
media-asset-management 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 7d 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media Asset Management
Design how images, video, and downloadable files get stored, processed, organized, and served. Stack-agnostic. The principles apply whether you're running a custom pipeline or using a hosted service.
When to use
- Designing or redesigning the image and media pipeline
- Choosing a media CDN or image service
- Setting up responsive image delivery
- Planning a digital asset management (DAM) system
- Auditing media performance issues
- Picking video hosting and embedding strategy
- Setting up workflows for designers and writers to upload assets
- Migrating media from one platform to another
When NOT to use
- Performance optimization beyond media (use
performance-optimization) - Brand identity or photography direction (use
brand-identity,art-direction) - Content production strategy (use
content-strategy) - Single-image optimization (covered in
performance-optimization)
Required inputs
- Current media inventory: where assets live, in what formats
- Volume: how many assets, how much storage, how much traffic
- Sources: who creates and uploads media (designers, writers, automated tools)
- Platforms: where media is consumed (web, email, app, partners)
- Performance baseline: current image sizes, load times
- Budget reality: hosted services have monthly costs
The framework: 4 stages
The media pipeline has four stages. Each has its own decisions.
Stage 1: Source
Where assets enter the system.
Sources:
- Designers (Figma exports, Photoshop, Illustrator)
- Photographers (RAW or JPEG from camera)
- Stock photo libraries
- AI-generated images
- User-generated content (uploads)
- Automated systems (e.g., screenshots, generated thumbnails)
At source, decide:
- File formats accepted (RAW, TIFF, PSD, AI vs delivered formats)
- Naming conventions
- Required metadata (alt text, captions, credits, rights)
- Maximum source resolution (high enough to derive any size; not so high it's wasteful)
- Where source files live (separate from delivered assets)
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.
- 7d ago First seen · 312 lines · 111 tokens per session scan A 85055e955d5b
media-asset-management is a skill published in the GitHub repository rampstackco/claude-skills (838 stars, last pushed 3d ago), licensed MIT. It adds 111 tokens to every session and 2,722 once invoked, about $0.0006 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.
Other skills, from other repositories
image-crop-rotate
Image processing skill for cropping images to 50% from center and rotating them 90 degrees clockwise. This skill should be used when users request image cropping to center, image rotation, or both operations combined on image files.
suede-ad-creative
Suede-owned paid-media creative system for hooks, headlines, primary text, static and motion concepts, platform specs, review pages, and test-ready variant batches. Use when producing or iterating ad creative from grounded product and audience inputs. NOT FOR: campaign budgets, bidding, or targeting (use suede-ads)…
suede-image
Suede-owned marketing image production for generation prompts, hero and social graphics, product mockups, export sizing, compression, and preview assets. Use when the user needs a general-purpose marketing image or an image-production workflow. NOT FOR: paid-ad creative systems (use suede-ad-creative), video…
suede-rights-passport
Suede Labs skill that turns messy creator materials into a local, offline rights-and-provenance transfer package: inventoried and hashed assets, a normalized suede-intake.json manifest, credits and splits, license notes, provenance, and a missing-information report, validated by a bundled stdlib script. Use when a…
suede-video
Suede-owned marketing video planning and production discipline. Use when choosing a format, scripting, storyboarding, generating, editing, reverse-engineering pacing, building a repeatable video pipeline, or repurposing one source into multiple cuts. NOT FOR: deciding the social calendar (use suede-social), paid ad…
suede-sync-packaging
Suede Labs skill that prepares a song for sync pitching: scene and emotional angles, a supervisor-facing one-sheet, an exists/missing/unknown asset checklist covering master, instrumental, clean, and stems, screened lyric flags, mood tags, and the open clearance questions kept in their own labeled pile. Use when a…