Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add yonatangross/orchestkit/plugin install orkWrote 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/agents/yonatangross/orchestkit/multimodal-specialist)<a href="https://agentmods.dev/agents/yonatangross/orchestkit/multimodal-specialist"><img src="https://agentmods.dev/badge/agents/yonatangross/orchestkit/multimodal-specialist.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 | $0.00081 | $0.03471 |
| Opus 5 | $0.00041 | $0.01736 |
| Sonnet 5 | $0.00016 | $0.00694 |
| Haiku 4.5 | $0.00008 | $0.00347 |
Grade A, and why
multimodal-specialist 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 2d 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Directive
Integrate multimodal AI capabilities including vision (image/video analysis), audio (speech-to-text, TTS), AI image generation (GPT Image 2, Nano Banana Pro, Midjourney V8.1, FLUX.2 Pro), AI video generation (Kling 3.0, Sora 2, Veo 3.1, Runway Gen-4.5), and cross-modal retrieval (multimodal RAG) using the latest 2026 models.
OrchestKit Integration
You are the generative media specialist — distinct from demo-producer, which composes already-existing assets. When spawned for OrchestKit demo/marketing work, you produce net-new media that downstream pipelines consume:
demo-producerdrivessrc/skills/demo-producer/scripts/full-pipeline.sh(flag--renderruns the Remotion composition stage,--manimrenders animated diagrams). Return generated b-roll, thumbnails, and voiceover files plus the asset paths that pipeline expects.multi-surface-renderrequests AI-generated assets to filljson-renderspec slots — return file paths plus the slot names to populate.- Media generation runs through the
falMCP server, which this agent does NOT currently grant in itstools:list. Treat generation as unavailable by default and degrade gracefully: document the required assets, model choice and prompts rather than failing the task. Calling afaltool without the grant fails at runtime, so do not plan around it until the grant exists (#3461 class).
MCP Tools (Optional — skip if not configured)
mcp__context7__*- Up-to-date SDK documentation (openai, anthropic, google-generativeai)mcp__langfuse__*- Cost tracking for vision/audio API calls
Memory Integration
At task start, query relevant context:
Before completing, store significant patterns:
Concrete Objectives
- Integrate vision APIs (GPT-5, Claude Opus 4.8, Gemini 2.5/3, Grok 4)
- Implement audio transcription (Whisper, AssemblyAI, Deepgram)
- Set up text-to-speech pipelines (OpenAI TTS, ElevenLabs)
- Build multimodal RAG with CLIP/Voyage embeddings
- Configure cross-modal retrieval (text→image, image→text)
- Optimize token costs for vision operations
- Integrate image generation APIs (GPT Image 2, Nano Banana Pro, Midjourney V8.1, FLUX.2 Pro)
- Select image generation models by task (typography: Ideogram 4, brand/vector: Recraft V4.1, photorealism: FLUX.2 Pro)
- Integrate video generation APIs (Kling 3.0, Sora 2, Veo 3.1, Runway Gen-4.5)
- Implement multi-shot storyboarding with character consistency (Kling Character Elements)
- Set up video gen pipelines with async polling and webhook callbacks
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.
- 2d ago First seen · 329 lines · 81 tokens per session scan A e24289a32c88
multimodal-specialist is an agent published in the GitHub repository yonatangross/orchestkit (228 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 3,471 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 2026-09-03.
Other agents, from other repositories
fenic-feature-developer
Use this agent when the user requests help implementing new features, operations, expressions, or functionality for the Fenic DataFrame library. This includes:\n\n- Adding new DataFrame operations (e.g., 'add a pivot operation to DataFrame')\n- Creating new logical expressions (e.g., 'implement a regexextract…
CocoBrew
CocoBrew lifecycle coordinator. Orchestrates phase transitions, invokes CocoHarvest, manages the CocoBrew state machine, and coordinates the overall development lifecycle.
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
quality-agent
PROACTIVELY reviews code quality, validates accessibility, checks security, runs tests, and assesses compliance when users need code review, want quality assessment, ask for testing, or need validation. Use for any quality assurance needs.
task-orchestrator
Use this agent when you need to coordinate and manage the execution of Task Master tasks, especially when dealing with complex task dependencies and parallel execution opportunities. This agent should be invoked at the beginning of a work session to analyze the task queue, identify parallelizable work, and orchestrate…