domain-multimodal

domain-multimodal is a skill for Claude Code, Codex from mxslr/mlcraft. It costs 115 tokens per session (453 once invoked), scanned A, original, MIT.

A guide for tasks that use more than one kind of input, usually images and text together. It covers matching images with text, answering questions about images, writing captions, and understanding documents or charts.

In plain words
What is it for?
Use it for image-text search, zero-shot image classification, visual question answering, captioning, visual chat, document understanding, chart analysis, and visual grounding.
Why use it?
It helps choose between models for similarity search, visual question answering, and detailed visual understanding, while checking whether generated answers are faithful.

Skill for Claude CodeCodex

Part of the mlcraft plugin — 23 skills, 1 command, 1 agent shipped together

Install

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.

agentmods
npx agentmods add skills/mxslr/mlcraft/domain-multimodal
Any agent
npx skills add mxslr/mlcraft --skill domain-multimodal
Clone the repo
git clone --depth 1 https://github.com/mxslr/mlcraft

Made for: Claude Code, Codex.

Or install mlcraft, the plugin that ships this one along with the rest of its 23 skills, 1 command, 1 agent.

Wrote 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.

agentmods badge for domain-multimodal

README.md
[![agentmods](https://agentmods.dev/badge/skills/mxslr/mlcraft/domain-multimodal.svg)](https://agentmods.dev/skills/mxslr/mlcraft/domain-multimodal)
Your own site
<a href="https://agentmods.dev/skills/mxslr/mlcraft/domain-multimodal"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/domain-multimodal.svg" alt="Measured on agentmods" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00115 $0.00453
Opus 5 $0.00057 $0.00227
Sonnet 5 $0.00023 $0.00091
Haiku 4.5 $0.00012 $0.00045

Measured 5d ago against content hash 7d4c83b1c428, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

domain-multimodal 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.

skills/domain-multimodal/SKILL.md · 24 lines

What it actually says

Multimodal (Vision-Language) - Method Selection

Try zero-shot first. Pretrained models often work with no training.

Decision table

Task Recommended Notes
Zero-shot classification or image-text retrieval CLIP or SigLIP (contrastive dual-encoder) embeddings plus cosine similarity; build an approximate nearest neighbor index for retrieval.
VQA, captioning, visual chat BLIP-2 (Q-Former plus a frozen LLM) or a LLaVA-family model instruction-tuned; adapt parameter-efficiently.
Fine detail, documents, or charts a high-resolution VLM or a document-specialized model small text and layout need high input resolution.
Custom domain adaptation LoRA on the VLM, or fine-tune CLIP with a contrastive loss small data.

Cross-cutting practice

  • Prompt design matters for VLMs. Start zero-shot and only fine-tune if it is insufficient.
  • Metrics: retrieval uses Recall@K; zero-shot classification uses accuracy; VQA uses VQA accuracy (open-ended VQA needs an LLM judge plus human checks); captioning uses CIDEr, SPICE, or BLEU plus human review.
  • Caveats: VLMs hallucinate, so evaluate faithfulness. Deduplicate to avoid train and test image overlap.
  • Explainability: cross-attention or grounding maps (which region the answer used), and retrieved neighbors for retrieval.
  • Improve results: use accuracy-improvement-loop; evaluate with rigorous-evaluation.
Changes

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.

  1. 5d ago First seen · 24 lines · 115 tokens per session scan A 7d4c83b1c428

Subscribe to this mod's changes

domain-multimodal is a skill published in the GitHub repository mxslr/mlcraft (8 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 453 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

transformers

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…

synthetic-sciences/openscience · 63 tokens

hailo-optimize

Optimize and quantize a parsed Hailo HAR using the Hailo Dataflow Compiler (DFC). Auto-loads a matching ALLS model script from the Model Zoo, prepares calibration data (with the correct normalization alignment), runs optimization on GPU when available, and gates on the post-optimize SNR.

hailo-ai/hailo_model_zoo · 67 tokens

hailo-parse

Parse an ONNX or TensorFlow model into a Hailo HAR using the Hailo Dataflow Compiler (DFC). Use when bringing a new model into the Hailo flow. Auto-discovers parser start/end nodes and normalization from the Model Zoo when the model name matches a known network.

hailo-ai/hailo_model_zoo · 65 tokens

hailo-compile

Compile an optimized Hailo HAR into a HEF binary using the Hailo Dataflow Compiler (DFC). Final stage of the DFC flow — takes the quantized HAR from /hailo-optimize and produces a deployable .hef.

hailo-ai/hailo_model_zoo · 55 tokens

chief-data-officer

Owns data as an asset — governance, quality, the warehouse and semantic layer, analytics capability, and the governance of models built on top. Use this for a decision about how data is collected, stored, defined, or shared; when numbers disagree between teams; when deciding what to build in-house versus buy; when…

cbrock84/headcount · 88 tokens

ai-workflow-architect

Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repetitive manual work, connect tools into a…

cbrock84/headcount · 89 tokens