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/jbertus/openart-mcp/openartnpx skills add jbertus/openart-mcp --skill openartgit clone --depth 1 https://github.com/jbertus/openart-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/jbertus/openart-mcp/openart)<a href="https://agentmods.dev/skills/jbertus/openart-mcp/openart"><img src="https://agentmods.dev/badge/skills/jbertus/openart-mcp/openart.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 5.1 | $0.00077 | $0.00977 |
| Opus 5 | $0.00039 | $0.00489 |
| Sonnet 5 | $0.00015 | $0.00195 |
| Haiku 4.5 | $0.00008 | $0.00098 |
Grade A, and why
openart 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 5d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenArt Skill
Pair to the openart-mcp server (https://github.com/jbertus/openart-mcp). OpenArt.ai has no public API, so the MCP drives the web UI via Playwright. This skill tells Claude when and how to call the MCP tools.
Tools available (from openart-mcp)
openart_list_characters— return every character in the user's accountopenart_get_character— fetch one character by IDopenart_create_character— create a new character from a local imageopenart_generate_video— generate a video of a character speaking a scriptopenart_get_video_status— poll a video render
Intent → tool routing
| User intent | Tool sequence |
|---|---|
| "What characters do I have on OpenArt?" / "list avatars" | openart_list_characters |
| "Show me [character name]" | openart_list_characters → openart_get_character |
| "Create a new OpenArt character" / "make an avatar from this image" | openart_create_character |
| "Make a video of [character] saying [script]" | openart_list_characters (to find ID) → openart_generate_video |
| "Is the video done?" / "check video status" | openart_get_video_status |
Argument tips
image_pathmust be an absolute local path (Playwright reads from disk).scriptis dialogue the avatar speaks. Cap ~200 words per 60s of intended video for natural pacing.aspect_ratiooptions:9:16(vertical/Reels/Shorts),16:9(landscape/YouTube),1:1(square).background_storywhen creating a character: persona, voice, mannerisms, wardrobe. OpenArt uses it for consistency across generations.voice_idis optional. If omitted, OpenArt assigns a default voice. List voices via the OpenArt UI to capture IDs.
Latency expectations
list_characters/get_character: 5–15s (browser launch + page load)create_character: 30–90s (upload + processing)generate_video: returns a job ID immediately; render takes 2–10 minutes; pollget_video_status
Common patterns
One-off video with an existing character
1. openart_list_characters
2. Pick the character ID matching the user's request
3. openart_generate_video { character_id, script, aspect_ratio }
4. openart_get_video_status { video_id } — poll every 30s until status == "complete"
5. Return the resulting video URL to the user
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.
- 5d ago First seen · 90 lines · 77 tokens per session scan A 3671960f9b2a
openart is a skill published in the GitHub repository jbertus/openart-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 977 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…
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…