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 Mark-Life/agent-skills --skill media-cdngit clone --depth 1 https://github.com/Mark-Life/agent-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/mark-life/agent-skills/media-cdn)<a href="https://agentmods.dev/skills/mark-life/agent-skills/media-cdn"><img src="https://agentmods.dev/badge/skills/mark-life/agent-skills/media-cdn/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/mark-life/agent-skills/media-cdn"><img src="https://agentmods.dev/badge/skills/mark-life/agent-skills/media-cdn.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00033 | $0.00849 |
| Opus 5 | $0.00016 | $0.00425 |
| Sonnet 5 | $0.00007 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
media-cdn 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 12d 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.
**Done when** the id and URL you report came from the command's own output, and — for anything published — a `curl -sS -o /dev/null -w '%{http_code}' "<url>"` with no `Authorization` header returned `200`. How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media CDN
scripts/cdn.ts covers every asset operation the service exposes: a private object store where each asset flips to a public CDN URL and back. Run it with Bun (preferred) or Node >= 22.18, from the skill's scripts/ dir:
bun cdn.ts upload ~/Downloads/diagram.png --public
Commands
| Command | What it does |
|---|---|
upload <file...> [--public] [--folder p] [--name f] [--type mime] |
Reserve, PUT bytes, mark ready, then publish when --public is given. Folder defaults to asset; --folder "" is the root. SHA-256 is checked server-side, so a truncated upload fails instead of storing a broken file. Each upload makes a new asset, even for a filename already in the workspace — list --match <name> first when replacing something, then publish the new id. |
list [--folder p] [--match s] [--public|--private] [--limit n] |
Every asset in the workspace, filtered client-side. |
get <ref> |
One asset, with its public URL when published. |
publish <ref> / unpublish <ref> |
Turn the public CDN URL on or off. Reversible either way. |
download <ref> [--out path] |
Writes the bytes to --out, or to the asset's filename in the cwd. Sends the API key, so it reaches private assets too. |
whoami |
Workspace id, token name, scopes — run this first when a call fails with 401 or 403. |
<ref> is an asset id or a case-insensitive filename substring matching exactly one asset; ambiguity prints the candidates and exits 1.
Credentials
MEDIA_CDN_API_URL and MEDIA_CDN_API_KEY come from ~/.agents/.env.local, overridden by the process environment, overridden by --env <path> on any command. Report error: MEDIA_CDN_API_URL and MEDIA_CDN_API_KEY must be set … to the user as a setup gap and stop — keys are theirs to add. Keep the key out of chat, out of logs, and out of any file you write.
Output contract
Default output is one tab-separated line per asset, built for cut -f:
<id>\t<public-url or ->\t<filename> # upload, get, publish, unpublish
<id>\t<public-url or ->\t<filename>\t<bytes>\t<folder> # list
What ships with it
3 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.
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.
- 12d ago First seen · 49 lines · 33 tokens per session scan A c0ffe0b495e0
media-cdn is a skill published in the GitHub repository Mark-Life/agent-skills (2 stars, last pushed 28d ago), licensed MIT. It adds 33 tokens to every session and 849 once invoked, about $0.0002 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.
Other skills, from other repositories
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…