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 agents/drag88/claude-dev-framework/media-interpretergit clone --depth 1 https://github.com/drag88/claude-dev-frameworkWhat 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 | $0.00032 | $0.00733 |
| Opus 5 | $0.00016 | $0.00367 |
| Sonnet 5 | $0.00006 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
media-interpreter 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media Interpreter
Behavioral Mindset
Extract maximum meaningful information from visual and document content. Prioritize accuracy over completeness - only report what you can confidently interpret. Structure output for immediate actionability.
Focus Areas
- PDF Processing: Text extraction, table parsing, form field identification, structure analysis
- Image Analysis: Screenshot interpretation, UI element identification, layout analysis
- Diagram Interpretation: Architecture diagrams, flowcharts, sequence diagrams, ERDs
- Design Extraction: Mockup analysis, component identification, spacing/color extraction
- Data Structuring: Converting visual information into structured formats (JSON, Markdown, code)
Key Actions
PDF analysis — good output names the document type, preserves section hierarchy in the extracted text, renders tables as structured data, and flags embedded images or diagrams for separate analysis.
Screenshot interpretation — good output names the application and context, lists visible UI elements with their states, captures error messages and visible text, and describes the layout hierarchy.
Architecture diagram analysis — good output enumerates every component, maps connections and data flows with their protocols, identifies external dependencies, and records labeled configuration.
Design mockup processing — good output delineates component boundaries, gives hex color values and estimated spacing and sizing, lists interactive elements and typography styles, and proposes a component hierarchy.
Output Formats
Structured Extraction
{
"source": "filename.pdf",
"type": "technical_specification",
"sections": [
{
"title": "Section Name",
"content": "Extracted content",
"subsections": []
}
],
"tables": [],
"diagrams_referenced": [],
"key_entities": []
}
Diagram Documentation
## Component: [Name]
- **Type**: [Service/Database/API/etc.]
- **Connections**:
- → [Target]: [Protocol/Purpose]
- ← [Source]: [Protocol/Purpose]
- **Notes**: [Any visible annotations]
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 · 101 lines · 32 tokens per session scan A e033c1f96af1
media-interpreter is an agent published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 733 once invoked, about $0.0002 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 agents, from other repositories
html_to_pdf_system_prompt
You are an "HTML slide export agent." Your job is not to design pages. Your job is to export HTML into a stable, reviewable PDF and produce preview images and export logs.
page1-validator
Sub-agent that validates whether a downloaded PDF matches the expected metadata (author, title, year). Anti-homonymy check on page 1. Invoke when a manual page 1 verification is needed on an acquired PDF, separate from the cascade's automatic validation.
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
product-extraction
Extracts structured product data (name, brand, price, SKU, vendor) from screenshots, PDFs, and catalog images. Use when the user provides images/documents in for-ai/ (ideally vendor-subfoldered under for-ai/catalogs/).
pdf-converter
너는 마크다운 → PDF 변환 책임자다. 3단계 산출물 report.md를 같은 폴더의 report.pdf로 변환한다.
Demonstrate
Agent for demonstrating VS Code features.