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.
npx skills add carsxe/carsxe-claude-plugin --skill vin-ocrgit 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/skills/carsxe/carsxe-claude-plugin/vin-ocr)<a href="https://agentmods.dev/skills/carsxe/carsxe-claude-plugin/vin-ocr"><img src="https://agentmods.dev/badge/skills/carsxe/carsxe-claude-plugin/vin-ocr/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/skills/carsxe/carsxe-claude-plugin/vin-ocr"><img src="https://agentmods.dev/badge/skills/carsxe/carsxe-claude-plugin/vin-ocr.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 | $0.00042 | $0.00235 |
| Opus 5 | $0.00021 | $0.00118 |
| Sonnet 5 | $0.00008 | $0.00047 |
| Haiku 4.5 | $0.00004 | $0.00023 |
Grade A, and why
vin-ocr 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
When the user shares an image containing a VIN (photo of dashboard, door jamb, windshield, etc.):
- Make an HTTP POST request to the CarsXE VIN OCR API:
- URL:
https://api.carsxe.com/v1/vinocr?key={CARSXE_API_KEY}&source=claude_plugin - Headers:
Content-Type: application/json - Body:
{ "imageUrl": "{IMAGE_URL}" }
- URL:
- Display the extracted VIN and confidence score.
- Offer to immediately decode the VIN using the vehicle-specs skill.
- If the image quality is poor or the VIN can't be extracted, suggest the user try a clearer photo with better lighting and angle.
- If the API key is missing, tell the user to set the
CARSXE_API_KEYenvironment variable.
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 · 21 lines · 42 tokens per session scan A 782d89366e06
vin-ocr is a skill published in the GitHub repository carsxe/carsxe-claude-plugin (2 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 235 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 skills, from other repositories
camclave
Consent-gated webcam access so the agent can see a single still frame from the user's camera while the user watches a live preview. NO VIDEO CAPTURE — every frame on disk is an explicit, on-demand PNG. Use for hardware testing, OCR, plant logs, posture coaching, instrument reading. Includes adjust for tweaking camera…
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.