rendertrust: Command for Gemini CLI

.gemini/commands/media/analyze-images.toml

analyze-images is a command for Gemini CLI from bybren-llc/rendertrust. It costs 0 tokens per session (414 once invoked), scanned A, a copy of analyze-images, Apache-2.0.

A command that examines images in a directory and writes a report describing their content, visible text, colours, and composition. It can also suggest filenames and, when requested, rename or organise files.

In plain words
What is it for?
Use it to inspect PNG, JPG, GIF, WEBP, SVG, or BMP files, identify their contents, and create descriptive filenames.
Why use it?
It avoids reviewing many image files one by one and puts the results in a consistent report.

Command for Gemini CLI

Written for Gemini CLI: installed under .gemini/. Also seen: mentions Gemini CLI.

This is bybren-llc/rendertrust's own configuration. It tells Gemini CLI how to work on rendertrust itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rendertrust configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is /media:analyze-images ./assets/icons.

Reuse

Borrowing it

Nothing to install: this file belongs to bybren-llc/rendertrust. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bybren-llc/rendertrust/dev/.gemini/commands/media/analyze-images.toml
Clone the repo
git clone --depth 1 https://github.com/bybren-llc/rendertrust

Made for: Gemini CLI.

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 analyze-images

README.md
[![agentmods](https://agentmods.dev/badge/commands/bybren-llc/rendertrust/analyze-images.svg)](https://agentmods.dev/commands/bybren-llc/rendertrust/analyze-images)
Your own site
<a href="https://agentmods.dev/commands/bybren-llc/rendertrust/analyze-images"><img src="https://agentmods.dev/badge/commands/bybren-llc/rendertrust/analyze-images.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 414 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.00414
Opus 5 $0.00000 $0.00207
Sonnet 5 $0.00000 $0.00083
Haiku 4.5 $0.00000 $0.00041

Measured yesterday against content hash 269b1e4d6b24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

analyze-images 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 yesterday.

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.

Origin

This is a copy

100% identical to analyze-images — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.gemini/commands/media/analyze-images.toml · 72 lines

What it actually says

description = "Analyze and describe images in a directory"

prompt = """

Analyze Images Command

Analyze images in the specified directory using Gemini's multimodal vision capabilities.

Target: {{args}}

Supported Formats

PNG, JPG, JPEG, GIF, WEBP, SVG, BMP

Workflow

1. Discover Images

Find all images in the target directory:

!{find {{args}} -type f \\( -iname "*.png" -o -iname "*.jpg" -o -iname "*.jpeg" -o -iname "*.gif" -o -iname "*.webp" -o -iname "*.svg" -o -iname "*.bmp" \\) 2>/dev/null | head -20}

2. Analyze Each Image

For each image found:

  1. Read the image file using multimodal input
  2. Describe the visual content
  3. Identify key elements (objects, text, colors, composition)
  4. Suggest appropriate filename based on content

3. Generate Report

Create a markdown report with:

## Image Analysis Report

### image1.png
- **Description**: [Visual description]
- **Key Elements**: [Objects, text, colors identified]
- **Suggested Name**: [content-based-name.png]
- **Dimensions**: [if available]

### image2.jpg
...

Output Options

Based on user request, can also:

  • Rename files based on content
  • Organize into category folders
  • Extract text from images (OCR)
  • Generate alt-text for accessibility
  • Create thumbnails descriptions

Usage Examples

/media:analyze-images ./screenshots
/media:analyze-images ~/Downloads/images
/media:analyze-images ./assets/icons

Notes

  • Gemini CLI multimodal: Images are base64-encoded for model consumption
  • Large directories: Process in batches of 10-20 images
  • Privacy: Image contents are sent to Gemini API for analysis """
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. yesterday First seen · 72 lines · 0 tokens per session scan A 269b1e4d6b24

Subscribe to this mod's changes

analyze-images is a command published in the GitHub repository bybren-llc/rendertrust (7 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 414 tokens. A static security scan graded it A with 0 findings. It is 100% identical to analyze-images, differing in 0 lines, and is treated as a copy.