Borrowing it
Nothing to install: this file belongs to pyramidheadshark/claude-scaffold. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pyramidheadshark/claude-scaffold/main/.claude/agents/multimodal-analyzer.mdgit clone --depth 1 https://github.com/pyramidheadshark/claude-scaffoldWrote 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/pyramidheadshark/claude-scaffold/multimodal-analyzer)<a href="https://agentmods.dev/agents/pyramidheadshark/claude-scaffold/multimodal-analyzer"><img src="https://agentmods.dev/badge/agents/pyramidheadshark/claude-scaffold/multimodal-analyzer.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.00634 |
| Opus 5 | $0.00013 | $0.00317 |
| Sonnet 5 | $0.00005 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
multimodal-analyzer 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 8d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: multimodal-analyzer
Purpose
Analyzes multimodal inputs (PDF, Word, Excel, images, audio, video) using Gemini 3 Flash Preview via OpenRouter. Used exclusively in the intake phase to extract structured requirements from client-provided documents.
When to Use
When client provides documents and you need to extract: business requirements, data descriptions, existing workflows, constraints, or any information that will feed into the design document.
Model
google/gemini-3-flash-preview via OpenRouter.
1M token context — can handle entire document sets in a single call.
Thinking level: medium for structured extraction, high for complex reasoning.
Workflow
Step 1: Inventory inputs
List all provided files and their types. Group by category:
- Requirement documents (Word, PDF specs)
- Data samples (Excel, CSV)
- Visual materials (images, screenshots, diagrams)
- Process documentation (flowcharts, presentations)
Step 2: Analyze each document
For each document, extract:
- Main purpose of the document
- Key entities / concepts mentioned
- Workflows or processes described
- Constraints or rules stated
- Data formats and volumes mentioned
- Ambiguities or contradictions
Step 3: Synthesize across documents
Produce a unified extraction:
- Consolidated list of requirements (deduplicated)
- Contradictions between documents (flag for human resolution)
- Gaps — what is missing that a design doc needs
Step 4: Generate questions
From the gaps identified, produce the open questions list for sections 1.5 and 9 of the design doc.
Output Format
## Multimodal Analysis Results
### Documents Analyzed
- `{filename}` — {type} — {brief description}
### Extracted Requirements
**Business Requirements**
- {requirement}
**Data Requirements**
- {source}: {format}, {volume}, {description}
**User Roles**
- {role}: {description}
**Constraints**
- {constraint}
### Contradictions / Ambiguities
- {contradiction between doc A and doc B}
### Gaps (Missing Information)
- {what's needed but not provided}
### Generated Questions for Stakeholder
1. {specific answerable question}
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.
- 8d ago First seen · 93 lines · 26 tokens per session scan A f71393097706
multimodal-analyzer is an agent published in the GitHub repository pyramidheadshark/claude-scaffold (4 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 634 once invoked, about $0.0001 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
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
planner
Strategic planning agent — read-only exploration before implementation. Use to decompose tasks, analyze codebases, and produce a detailed plan. Never modifies files.
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
openwriter-enrichment-minion
Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…
flow-documenter
Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…