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 sideshowroberto/vfx-agent-toolkit --skill magnific-image-gengit clone --depth 1 https://github.com/sideshowroberto/vfx-agent-toolkitWrote 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-image-gen)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/magnific-image-gen"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/magnific-image-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.
<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/magnific-image-gen"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/magnific-image-gen.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 | $0.00071 | $0.02812 |
| Opus 5.5 | $0.00028 | $0.01125 |
| Sonnet 5.5 | $0.00014 | $0.00562 |
| Haiku 4.5 | $0.00007 | $0.00281 |
Grade A, and why
magnific-image-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 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.
- Download with `creations_wait` -> URL -> `urllib.request.urlretrieve` (same as any generation) How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Magnific Image Generation Skill
Account Context
- Preferred models: Nano Banana 2 Pro and Flash - use these by default for concept work
- Check balance and plan coverage with
account_balanceif the user asks or before heavy batch runs (Pro unlimited plans cover NB2 at 1K/2K with no credit burn; 4K costs credits)
Two Rules Before Any Generation
- Confirm the destination folder. Team workspaces often have multiple similarly-named project folders (several people may each have created one for the same show). Before a batch run, state which folder you are generating into and confirm it - including the right subfolder (e.g. a per-artist subfolder). Never generate into the workspace root.
- On an auth/re-authorization error, stop - do not retry. Magnific MCP sessions expire mid-task. The error is not transient: tell the user to run
/mcpand re-authenticate, then resume from where you left off (re-request any presigned upload URLs, which go stale).
Model Selection Protocol
Always check models before generating if the user has not specified one.
1. Call images_models_list (optionally with search= to filter)
2. Read agentRecommendation fields
3. Default to NB2 Pro (high quality) or NB2 Flash (faster iteration)
4. Only use other models if the user has a specific reason
Priority Models for This Account
Default: NB2 Pro (imagen-nano-banana-2) for everything. Only drop to Flash if the user explicitly asks for faster iteration.
| Model | Slug | Speed | Best For |
|---|---|---|---|
| Nano Banana 2 Pro [OK] DEFAULT | imagen-nano-banana-2 |
~50s | All concept and final work - default choice |
| Nano Banana 2 Flash | imagen-nano-banana-2-flash |
~34s | When user wants faster iteration or batch drafts |
| Cinematic | cinematic |
~46s | Cinematic stills, when 4k quality is the priority |
| GPT 2 | gpt-2 |
~69s | Text/typography/infographics (not photorealistic) |
| Flux.1 Kontext Max | flux-kontext-high |
~13s | Quick edits with image refs when speed matters |
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 · 251 lines · 71 tokens per session scan A 43cae2201423
magnific-image-gen is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 71 tokens to every session and 2,812 once invoked, about $0.0003 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…