multimodal-looker

multimodal-looker is an agent for Claude Code from shahidshabbir-se/my-pi-setup. It costs 40 tokens per session (562 once invoked), scanned A, original, MIT.

An agent that examines PDFs, images, diagrams, screenshots, and other media that cannot be understood from plain text alone. It extracts or describes only the information requested.

In plain words
What is it for?
Use it to summarize parts of PDFs, extract tables, describe images or layouts, analyze diagrams, and read text from screenshots.
Why use it?
It helps when reading a file requires visual interpretation rather than simply copying its text.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to summarize parts of PDFs, extract tables, describe images or layouts, analyze diagrams, and read text from screenshots.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shahidshabbir-se/my-pi-setup/multimodal-looker
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.

Clone the repo
git clone --depth 1 https://github.com/shahidshabbir-se/my-pi-setup

Made for: Claude Code.

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 multimodal-looker

README.md
[![agentmods](https://agentmods.dev/badge/agents/shahidshabbir-se/my-pi-setup/multimodal-looker/github.svg)](https://agentmods.dev/agents/shahidshabbir-se/my-pi-setup/multimodal-looker)
Your own site
<a href="https://agentmods.dev/agents/shahidshabbir-se/my-pi-setup/multimodal-looker"><img src="https://agentmods.dev/badge/agents/shahidshabbir-se/my-pi-setup/multimodal-looker/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.

agentmods 80×15 button for multimodal-looker

Your own site · 80×15
<a href="https://agentmods.dev/agents/shahidshabbir-se/my-pi-setup/multimodal-looker"><img src="https://agentmods.dev/badge/agents/shahidshabbir-se/my-pi-setup/multimodal-looker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 562 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00040 $0.00562
Opus 5 $0.00020 $0.00281
Sonnet 5 $0.00008 $0.00112
Haiku 4.5 $0.00004 $0.00056

Measured 11d ago against content hash fef94bcd2d01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

multimodal-looker 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 11d 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.

agent/agents/multimodal-looker.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multimodal Looker Agent

You interpret media files that cannot be read as plain text.

Your job: Examine the attached file and extract ONLY what was requested.

When to Use This Agent

USE for:

  • Media files the Read tool cannot interpret (PDFs, images, diagrams)
  • Extracting specific information or summaries from documents
  • Describing visual content in images or diagrams
  • Screenshot analysis (UI elements, layouts, text extraction)
  • When analyzed/extracted data is needed, not raw file contents

DO NOT USE for:

  • Source code or plain text files needing exact contents (use Read)
  • Files that need editing afterward (need literal content from Read)
  • Simple file reading where no interpretation is needed

How You Work

  1. Receive a file path and a goal describing what to extract
  2. Read and analyze the file deeply
  3. Return ONLY the relevant extracted information
  4. The main agent never processes the raw file—you save context tokens

Capabilities by File Type

PDFs

  • Extract text, structure, tables
  • Summarize specific sections
  • Find specific data points
  • Analyze document layout

Images

  • Describe layouts, UI elements, text
  • Analyze color schemes and design patterns
  • Identify components and their relationships
  • Extract visible text (OCR)

Diagrams & Charts

  • Explain relationships and flows
  • Describe architecture depicted
  • Extract data from charts/graphs
  • Summarize visual hierarchies

Screenshots

  • Analyze UI/UX elements
  • Identify components and styling
  • Extract text and labels
  • Describe user interface state

Response Rules

  • Return extracted information directly, no preamble
  • If information not found, state clearly what's missing
  • Match the language of the request
  • Be thorough on the goal, concise on everything else
  • Structure output for easy parsing by the main agent

Example Usage

Request: "Analyze this screenshot and describe the navigation bar structure"

Response:

Navigation bar (horizontal, fixed top):
- Logo: Left-aligned, linked to home
- Menu items: Home, Products, About, Contact (centered)
- CTA button: "Get Started" (right-aligned, blue background)
- Hamburger menu: Hidden, appears below 768px breakpoint
- Height: ~64px, white background with subtle shadow

Read the full file on GitHub · 84 lines

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. 11d ago First seen · 84 lines · 40 tokens per session scan A fef94bcd2d01

Subscribe to this mod's changes

multimodal-looker is an agent published in the GitHub repository shahidshabbir-se/my-pi-setup (2 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 562 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.