media-interpreter — Claude Code subagent
media-interpreter — a subagent for working with PDFs, images, diagrams, and other binary formats. Extracts text, tabular data, and descriptions of visual content when standard file reading isn't an option.
no license ★ 1,064 updated 2026-01-21
.claude/agents/media-interpreter.mdWhat media-interpreter does
media-interpreter runs when you need information from a file that Read cannot parse as plain text — PDFs, error screenshots, architecture diagrams, financial reports with tables. The subagent analyzes a file based on your specific goal and returns only the relevant data: extracted text, structured tables, descriptions of UI elements, or relationships between diagram components.
The subagent has access to web search, code context, and repository tools to verify or supplement extracted information when needed. It never exposes raw file contents to the main agent — only what you requested — to conserve context tokens.
Do not use media-interpreter for source code, plain text, markdown, or JSON; use Read instead. This subagent is for cases where Read would return garbled output or when you need selective data from a complex document.
What it helps with
- pull text and tables from a PDF document
- read an error from a screenshot and describe its context
- analyze an architecture diagram and explain service connections
- extract structured data from a financial report or registry
- describe a UI mockup from an image
Example prompts for the agent
- Which authentication methods are listed in
docs/api-spec.pdf? Use media-interpreter. - I have an error screenshot at
error.png. Identify and describe what's happening. - Explain how the services communicate based on
architecture.png.
How to install media-interpreter
Manually: put the files in place
.claude/agents/media-interpreter.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/media-interpreter.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/media-interpreter.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about media-interpreter
How do I install media-interpreter in Claude Code?
Add the subagent config to .claude/agents/media-interpreter.md. Copy the media-interpreter description and settings from the jarrodwatts/claude-code-config repository.
When should I use media-interpreter instead of Read?
Use media-interpreter when Read returns garbled output (for PDFs, images, diagrams), when you need selective data from a document, or when you need a description of visual content. For source code, plain text, and JSON, use Read.
What file types can media-interpreter analyze?
PDF documents, images (PNG, JPG), diagrams, tables within documents, screenshots, architecture diagrams, charts, and any format that cannot be read as plain text.