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/carsxe/carsxe-claude-pluginWrote 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/commands/carsxe/carsxe-claude-plugin/images)<a href="https://agentmods.dev/commands/carsxe/carsxe-claude-plugin/images"><img src="https://agentmods.dev/badge/commands/carsxe/carsxe-claude-plugin/images/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/commands/carsxe/carsxe-claude-plugin/images"><img src="https://agentmods.dev/badge/commands/carsxe/carsxe-claude-plugin/images.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 | $0.00000 | $0.00460 |
| Opus 5 | $0.00000 | $0.00230 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
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 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.
What it actually says
CarsXE — Vehicle Images
Retrieve images for a vehicle using the CarsXE Images API.
Steps
-
Parse $ARGUMENTS to extract:
make(required): vehicle manufacturer (e.g., BMW, Ford, Toyota)model(required): vehicle model (e.g., X5, Mustang, Camry)year(optional): 4-digit year (e.g., 2019)trim(optional): specific trim level (e.g., Sport, Limited)color(optional): vehicle color (e.g., red, black)transparent(optional):trueto return transparent background imagesangle(optional):front,side, orbackphotoType(optional):interior,exterior, orenginesize(optional):Small,Medium,Large,Wallpaper, orAlllicense(optional):Public,Share,ShareCommercially,Modify, orModifyCommercially
Example:
/carsxe:images BMW X5 2019 -
If
makeormodelare missing, ask the user to provide them. -
Make an HTTP GET request:
GET https://api.carsxe.com/images?key=<CARSXE_API_KEY>&make=<MAKE>&model=<MODEL>&source=claude_plugin[&year=<YEAR>][&trim=<TRIM>][&color=<COLOR>][&transparent=<TRANSPARENT>][&angle=<ANGLE>][&photoType=<PHOTOTYPE>][&size=<SIZE>][&license=<LICENSE>]Replace
<CARSXE_API_KEY>with the value of the environment variableCARSXE_API_KEY. Only include optional parameters if the user specified them. -
Present the results:
- List all returned image URLs
- Display each image inline if the environment supports it
- Label each image with angle/type if available
-
Handle errors gracefully (no images found, invalid params, auth error).
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 · 37 lines · 0 tokens per session scan A 3d92b4013b0c
images is a command published in the GitHub repository carsxe/carsxe-claude-plugin (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 460 tokens. 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 commands, from other repositories
me-build-slides
Build a graphics-first thermal-fluid research presentation with slide-to-slide logic, visual plans, speaker notes, and backup-slide structure.
video-maker
A command for creating videos by writing React components with Remotion, a framework that renders code into video files. It can set up projects, create or edit video scenes, and render them.
pn-quieter
Reduce visual decoration — animations, colors, shadows, effects — without removing content. Use when there's too much visual noise. For content and feature reduction, use pn-distill.
brand-generate
Generate an on-brand document from a saved Brand Profile.
list
List available Piper TTS TTS voices with optional filtering.
transcribe
Transcribe the file at $ARGUMENTS into Markdown using the Frenchie MCP server.