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 agentmods add skills/1raghavm/visualgen-mcp/visualgennpx skills add 1RaghavM/visualgen-mcp --skill visualgengit clone --depth 1 https://github.com/1RaghavM/visualgen-mcpWrote 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/1raghavm/visualgen-mcp/visualgen)<a href="https://agentmods.dev/skills/1raghavm/visualgen-mcp/visualgen"><img src="https://agentmods.dev/badge/skills/1raghavm/visualgen-mcp/visualgen.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.01730 |
| Opus 5 | $0.00039 | $0.00865 |
| Sonnet 5 | $0.00016 | $0.00346 |
| Haiku 4.5 | $0.00008 | $0.00173 |
Grade A, and why
visualgen 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 4d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
visualgen
When to use this skill
You are about to call any of the visualgen-mcp tools (submit_video, check_video, list_videos, generate_image, list_images, get_pricing), or the user asked you to add / generate / iterate on visuals (images or video) in a web-design context. Load this skill once, apply its rules for the rest of the session.
Decision tree
- Image or video? If the user wants motion — a loop, a demo, a cinematic moment — use
submit_video. Otherwise usegenerate_image. Still images are ~100× cheaper and ~10× faster; default to image unless motion is the point. - Aspect ratio. Match the target surface:
- Hero, banner, desktop landing →
16:9 - Mobile hero, story, reel →
9:16 - Avatar, icon, square card →
1:1 - Inline content illustration →
4:3or3:4 - OG / Twitter card → closest to 16:9 (native is 1200×630; the server doesn't support 1.91:1 so use
16:9and crop in CSS)
- Hero, banner, desktop landing →
- Model tier — image. Draft with
nano-banana($0.039/image). Upgrade toimagenwhen you need anegative_promptor higher fidelity. - Model tier — video. Draft with
lite($0.05–$0.08/sec, 720p/1080p only — 4k is unsupported on this tier). Ship withfast($0.10–$0.12/sec at 720p/1080p,$0.30/sec at 4k). Only usestandard($0.40/sec at 720p/1080p,$0.60/sec at 4k) when the draft has proved the concept and the user has approved the higher cost. negative_prompt. Nano Banana ignores it. Imagen and Veo honor it. Use it when drafts keep including a specific unwanted element (text overlays, watermarks, specific colors, extra limbs, motion blur).- Image-to-video. Pass
image_pathtosubmit_videowhen you want motion that matches an existing still — typically after generating a hero image and wanting a matching loop variant.
Workflow rules
- Price once per session. Call
get_pricingon the first gated call, cache the numbers in your context, don't call it again in the same session unless the user asks. - Gate expensive calls. For Veo
standardor any image-to-video call, state the estimated cost and ask the user to confirm before submitting. Use this exact format:
What ships with it
8 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.
- 4d ago First seen · 73 lines · 79 tokens per session scan A 94665db4ad60
visualgen is a skill published in the GitHub repository 1RaghavM/visualgen-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 1,730 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…