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 yonatangross/orchestkit --skill multimodal-llmgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/multimodal-llm)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/multimodal-llm"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/multimodal-llm/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/yonatangross/orchestkit/multimodal-llm"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/multimodal-llm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.02443 |
| Opus 5.5 | $0.00033 | $0.00977 |
| Sonnet 5.5 | $0.00016 | $0.00489 |
| Haiku 4.5 | $0.00008 | $0.00244 |
Grade A, and why
multimodal-llm 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 20d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multimodal LLM Patterns
Integrate vision, audio, and video generation capabilities from leading multimodal models. Covers image analysis, document understanding, real-time voice agents, speech-to-text, text-to-speech, and AI video generation (Kling v3, Sora 2, Veo 3.1 std/lite/fast tiers, Runway Gen-4.5 via gen4_turbo).
Canonical model IDs (Google IDs checked against ai.google.dev/gemini-api/docs/models on 2026-09-23):
Provider Model IDs Anthropic claude-opus-5-5(recommended, the default Opus since CC 2.1.280, same 2,576 px budget as Opus 5),claude-opus-5,claude-opus-4-8,claude-opus-4-7,claude-opus-4-6,claude-sonnet-5-5,claude-sonnet-4-6,claude-haiku-4-5-20251001.claude-fable-5is Anthropic's frontier tier above Opus (GA 2026-07). Premium cost, never auto-pin it; the fable-spend-consent gate requires explicit user consent before any Fable spendOpenAI gpt-5.5(current flagship)gemini-3.1-pro-preview(flagship),gemini-3.1-flash-lite(cost)Veo veo-3.1-generate-preview/veo-3.1-lite-generate-preview/veo-3.1-fast-generate-previewKling kling-v3(model_name field in Kling API)Runway gen4_turbo(product label: Gen-4.5)
Quick Reference
| Category | Rules | Impact | When to Use |
|---|---|---|---|
| Vision: Image Analysis | 1 | HIGH | Image captioning, VQA, multi-image comparison, object detection |
| Vision: Document Understanding | 1 | HIGH | OCR, chart/diagram analysis, PDF processing, table extraction |
| Vision: Model Selection | 1 | MEDIUM | Choosing provider, cost optimization, image size limits |
| Audio: Speech-to-Text | 1 | HIGH | Transcription, speaker diarization, long-form audio |
| Audio: Text-to-Speech | 1 | MEDIUM | Voice synthesis, expressive TTS, multi-speaker dialogue |
| Audio: Model Selection | 1 | MEDIUM | Real-time voice agents, provider comparison, pricing |
| Video: Model Selection | 1 | HIGH | Choosing video gen provider (Kling, Sora, Veo, Runway) |
| Video: API Patterns | 1 | HIGH | Async task polling, SDK integration, webhook callbacks |
| Video: Multi-Shot | 1 | HIGH | Storyboarding, character elements, scene consistency |
What ships with it
12 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.
- rules/_sections.md 1.5 KB
- rules/_template.md 339 B
- rules/audio-models.md 3.3 KB
- rules/audio-speech-to-text.md 2.8 KB
- rules/audio-text-to-speech.md 2.7 KB
- rules/video-generation-models.md 3.5 KB
- rules/video-generation-patterns.md 4.1 KB
- rules/video-multi-shot.md 4.1 KB
- rules/vision-document.md 2.3 KB
- rules/vision-image-analysis.md 3.2 KB
- rules/vision-models.md 3.0 KB
- test-cases.json 7.9 KB
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.
- 20d ago Changed · -1 lines 1b871db4e3d0
- 28d ago Changed · -5 lines 9f27b7fdef2e
- 29d ago Changed · -1 lines cf701eca851b
- 1mo ago Changed 34a580ea173a
- 1mo ago Changed 81bb5b8061ec
- 1mo ago Changed 8e2864bcb0a4
- 1mo ago First seen · 190 lines · 82 tokens per session scan A 8c754eca6e3d
multimodal-llm is a skill published in the GitHub repository yonatangross/orchestkit (298 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 2,443 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
natural
Render the provided prompt template with Jinja context and send it to the active NPC's LLM. The rendered text becomes the user prompt; the LLM response is placed in context['output'].
trace-health
Compute CocoTrace Snowflake asset health grade. Usage: $trace health.
examples-qa
Verify Instructor behavior through the repository's ./examples/ suite in pass, live record, or hermetic replay mode. Use when running selected examples or the corpus, capturing and reusing recorded LLM HTTP responses, diagnosing hub results, or distinguishing real errors, assertion failures, skipped examples, and…
neurolink-guide
Guide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features.
ml-llm-wiki
Use when answering questions from this machine-learning knowledge base. Triggers: questions about transformers, attention cost and efficiency, and long-context scaling; 'what do we know about attention', 'check the ML wiki'. Read-only querying of compiled knowledge; to add, update, supersede, lint, audit, or critique…
atlan-search
How to find things in the Atlan data catalog with the Atlan MCP tools — which of semanticsearch / searchassets / getassets / traverselineage / resolvemetadata / getusers to reach for, and the filter rules that make each one return the right answer. Use for any discovery ask over catalog metadata — "what data do we…