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.
git clone --depth 1 https://github.com/shahidshabbir-se/my-pi-setupWrote 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/shahidshabbir-se/my-pi-setup/multimodal-looker)<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.
<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>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 | $0.00040 | $0.00562 |
| Opus 5 | $0.00020 | $0.00281 |
| Sonnet 5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
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.
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
- Receive a file path and a goal describing what to extract
- Read and analyze the file deeply
- Return ONLY the relevant extracted information
- 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
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.
- 11d ago First seen · 84 lines · 40 tokens per session scan A fef94bcd2d01
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.
Other agents, from other repositories
technical-writer
Architecture Decision Records, API documentation, migration guides, runbooks, and technical documentation specialist. Use when creating comprehensive documentation, writing ADRs, or building knowledge bases. Trigger phrases: ADR, documentation, runbook, migration guide, technical writing, API docs, changelog…
audio-engineer
Expert audio engineer for recording, mixing, mastering, and sound design.
brand-strategist
Expert brand strategist for brand identity, positioning, naming, and brand guidelines.
video-producer
Expert video production specialist for planning, shooting, editing, and delivering video content.
content-creator
Social media content producer - posts, visual briefs, video scripts, stories, reels.
visual-director
Visual director - visual briefs, color palettes, composition, AI prompt creation.