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 gabrielmoreira/agent-skills-mirror --skill asset-importgit clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirrorWrote 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/gabrielmoreira/agent-skills-mirror/asset-import)<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/asset-import"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/asset-import/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/gabrielmoreira/agent-skills-mirror/asset-import"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/asset-import.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 | $0.00062 | $0.00814 |
| Opus 5 | $0.00031 | $0.00407 |
| Sonnet 5 | $0.00012 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
asset-import 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 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.
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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asset Import
This build runs the editor and its media server locally. There is no hosted import API, no CLI, and no OAuth: media enters the project through the editor UI or through the agent tools below. Pick the path by where the bytes live.
Path 1 — user's local files (primary)
Ask the user to drag the files into the editor (preview canvas or 我的素材 panel) or use the upload button. The local pipeline then runs automatically: streaming write to /media/uploads/, conditional transcode (≤1920 long edge, browser-friendly codec, ~8Mbps), audio extraction, and auto-transcription (ASR starts on upload). Do not ask the user to pre-convert, pre-trim, or transcode anything themselves — the pipeline handles it.
The agent cannot read the user's filesystem. If the user gives you a /Users/... or C:\... path, tell them to drop that file into the editor instead; you cannot fetch it.
Path 2 — public URLs (agent-driven)
Use download_media with a single URL or a batch array. The server fetches, stores under /media/uploads/, and registers pool assets. Prefer this for stock/web media the user pointed at. After download, the asset behaves like any other media-pool asset.
Path 3 — external host transfer
Call import_media with {"action":"create_session", "assetType":..., "filename":..., "contentType":..., "size":...}. It returns one short-lived upload slot bound to the current project, session, asset identity, basename, POST, MIME type, and exact byte count. A host-side script may upload to that exact URL with the declared headers. The agent sandbox cannot reach the user's localhost, so do not attempt the transfer from run_code.
The successful upload response returns an opaque receipt, echoed assetType, and uploaded path. Probe the uploaded path when exact duration, dimensions, fps, or audio presence are needed, then call finalize_uploaded_asset with the receipt, echoed assetType, measured media metadata, and durationInSeconds for audio/video/gif. The server resolves the authoritative hash, path, size, filename, and asset id. Finalize commits the asset but never starts ASR; after placing an audio/video asset on a track, invoke transcribe_track separately if transcription is desired. The asset is not present or usable before finalize succeeds. For missing-media replacement, pass the existing assetId to import_media; omit it for a new asset. Never construct /media/uploads/... yourself and never claim bytes are ready before the upload response.
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 · 36 lines · 62 tokens per session scan A 80e0f062d36e
asset-import is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 814 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.