Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sideshowroberto/vfx-agent-toolkitnpx agentmods add skills/sideshowroberto/vfx-agent-toolkit/magnific-local-uploadWrote 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/sideshowroberto/vfx-agent-toolkit/magnific-local-upload)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/magnific-local-upload"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/magnific-local-upload/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/sideshowroberto/vfx-agent-toolkit/magnific-local-upload"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/magnific-local-upload.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 | $0.00051 | $0.02587 |
| Opus 5.5 | $0.00020 | $0.01035 |
| Sonnet 5.5 | $0.00010 | $0.00517 |
| Haiku 4.5 | $0.00005 | $0.00259 |
Grade A, and why
magnific-local-upload 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 today.
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.
import urllib.request, pathlib, sys How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Magnific Local Upload Skill
Version: 1.2.1 Last Updated: 2026-09-09
Handles the full pipeline: local folder -> upload to Magnific -> move to folder -> use as generation references -> download output to local folder.
Upload Architecture
Magnific does not accept file paths directly. Local files require a 3-step presigned upload:
1. creations_request_upload(mimeType, count=N) -> N presigned PUT URLs + temp paths
2. Python: PUT each file's bytes to the upload URL the response gives you
3. creations_finalize_upload(uploads=[...paths], folderReference=...) -> creation identifiers
creations_upload_file is for host-attached files (ChatGPT-style uploads) - it does not work for local disk files. Always use the 3-step flow.
Which PUT target to use (API changed - read the response, not this doc)
PUT to whichever upload URL field the creations_request_upload response
actually contains. As of 2026-09-09 that is proxyUploadUrl only - the
directUploadUrl (GCS) field this skill used to mandate is no longer returned
(three 4-7 MB PNGs uploaded through the proxy at first attempt, 200 each).
Earlier in 2026 the response carried both and the proxy was the flaky one;
if directUploadUrl reappears, prefer it, but never stall looking for a
field that is not there.
Never re-PUT to the same URL after a failure - a repeat PUT to one target
is rate-limited (429). Request fresh targets with creations_request_upload
and retry from there.
MIME Type Map
| Extension | mimeType |
|---|---|
.jpg / .jpeg |
image/jpeg |
.png |
image/png |
.webp |
image/webp |
.mp4 |
video/mp4 |
.mov |
video/quicktime |
.webm |
video/webm |
Workflow 1 - Batch Upload from Folder
Step 1: Scan folder with Glob
Glob(pattern="D:/path/to/folder/*.png")
Step 2: Request all presigned URLs in one call
creations_request_upload(mimeType="image/png", count=8)
# Returns: { uploads: [ {proxyUploadUrl, path, mimeType, expiresAt}, ... ] } (2026-09 shape)
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.
- today First seen · 290 lines · 51 tokens per session scan A 0de51fcba01e
magnific-local-upload is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 51 tokens to every session and 2,587 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-02.
Other skills, from other repositories
dcc-cua
A routing guide for controlling application interfaces through the project’s DCC-CUA system. DCC applications are digital-content tools such as Maya, Blender, and Houdini.
mesh-ops
Cross-adapter polygon modeling recipe pack for the shared cross-DCC modeling vocabulary. Structured RECIPES.yaml entries for primitive creation, hard-surface edits, topology cleanup, UV generation, radial arraying, and material assignment. Reusable by every DCC adapter's mesh-ops skill (maya, blender, houdini, 3dsmax…
marketplace-publish-extension
Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an…
marketplace-create-extension
Infrastructure skill — scaffold a new marketplace extension package (SKILL.md + tools.yaml + scripts/) with MIT-0 licensing. Use when creating a publishable marketplace entry for any DCC host. Not for editing existing extensions or driving live DCC scenes — use domain skills for that.
clawhub-compat
Example skill — demonstrates full compatibility with the ClawHub/OpenClaw skill format. Use as a reference when creating skills for both the dcc-mcp-core ecosystem and ClawHub marketplace. Not intended for production use — this is an authoring reference only.
example-layered-skill
Example skill — reference implementation of the internal layered architecture pattern (Tools / Services / Utils) for complex skills with shared business logic. Use as a template when a skill outgrows a single scripts/execute.py file. Not intended for production use — see docs/guide/skills.md for the architectural…