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/Scandit/skillsWrote 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/plugins/scandit/skills/skills)<a href="https://agentmods.dev/plugins/scandit/skills/skills"><img src="https://agentmods.dev/badge/plugins/scandit/skills/skills/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/plugins/scandit/skills/skills"><img src="https://agentmods.dev/badge/plugins/scandit/skills/skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
scandit-sdk 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 16d 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
{
"name": "scandit-sdk",
"version": "1.1.5",
"description": "AI agent skills for integrating the Scandit Data Capture SDK — product selection, documentation, and implementation guides for barcode scanning, ID capture, and smart label capture.",
"author": {
"name": "Scandit",
"url": "https://www.scandit.com/"
},
"homepage": "https://docs.scandit.com",
"repository": "https://github.com/scandit/skills",
"license": "Apache-2.0",
"mcpServers": "./.mcp.json",
"keywords": [
"scandit",
"barcode",
"scanning",
"barcode-scanning",
"barcode-capture",
"sparkscan",
"matrixscan",
"matrixscan-ar",
"matrixscan-count",
"matrixscan-batch",
"label-capture",
"smart-label-capture",
"data-capture",
"ios",
"web",
"react-native",
"flutter",
"capacitor",
"cordova",
"dotnet",
"net",
"net-android",
"net-ios",
"maui",
"xamarin",
"sdk",
"smart-data-capture"
]
}
What it installs
The manifest is a name and a version. 86 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 8,463 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill id-bolt A 124 tokens
- Skill matrixscan-batch-net-maui A 108 tokens
- Skill scandit-xamarin-to-net-migration A 169 tokens
- Skill barcode-capture-net-maui A 151 tokens
- Skill id-capture-web A 95 tokens
- Skill matrixscan-count-cordova A 101 tokens
- Skill data-capture-sdk A 99 tokens
- Skill id-capture-net-ios A 139 tokens
- Skill id-capture-net-maui A 148 tokens
- Skill label-capture-net-maui A 142 tokens
- Skill matrixscan-ar-net-maui A 101 tokens
- Skill id-capture-kmp A 124 tokens
- Skill id-capture-net-android A 139 tokens
- Skill label-capture-net-android A 140 tokens
- Skill label-capture-net-ios A 140 tokens
- Skill matrixscan-ar-net-android A 95 tokens
- Skill matrixscan-ar-net-ios A 114 tokens
- Skill matrixscan-batch-net-ios A 104 tokens
- Skill matrixscan-count-net-android A 101 tokens
- Skill matrixscan-count-net-ios A 105 tokens
- Skill matrixscan-count-net-maui A 110 tokens
- Skill sparkscan-net-android A 106 tokens
- Skill sparkscan-net-ios A 107 tokens
- Skill sparkscan-net-maui A 120 tokens
- Skill barcode-capture-net-android A 116 tokens
- Skill id-capture-android A 101 tokens
- Skill id-capture-capacitor A 91 tokens
- Skill id-capture-cordova A 107 tokens
- Skill id-capture-ios A 117 tokens
- Skill id-capture-rn A 90 tokens
- Skill matrixscan-batch-net-android A 104 tokens
- Skill matrixscan-count-android A 94 tokens
- Skill barcode-capture-net-ios A 117 tokens
- Skill barcode-selection-kmp A 97 tokens
- Skill id-capture-flutter A 89 tokens
- Skill label-capture-android A 92 tokens
- Skill label-capture-flutter A 75 tokens
- Skill label-capture-ios A 79 tokens
- Skill label-capture-rn A 76 tokens
- Skill matrixscan-count-ios A 90 tokens
- Skill matrixscan-count-kmp A 103 tokens
- Skill sparkscan-kmp A 79 tokens
- Skill barcode-capture-android A 99 tokens
- Skill barcode-capture-capacitor A 125 tokens
- Skill barcode-capture-cordova A 122 tokens
- Skill barcode-capture-flutter A 87 tokens
- Skill barcode-capture-kmp A 89 tokens
- Skill barcode-capture-rn A 91 tokens
- Skill label-capture-capacitor A 77 tokens
- Skill label-capture-cordova A 80 tokens
- Skill label-capture-kmp A 125 tokens
- Skill matrixscan-ar-cordova A 89 tokens
- Skill matrixscan-ar-flutter A 71 tokens
- Skill matrixscan-ar-kmp A 108 tokens
- Skill matrixscan-ar-rn A 67 tokens
- Skill matrixscan-ar-web A 83 tokens
- Skill matrixscan-batch-capacitor A 114 tokens
- Skill matrixscan-batch-cordova A 83 tokens
- Skill matrixscan-batch-flutter A 76 tokens
- Skill matrixscan-batch-ios A 68 tokens
- Skill matrixscan-batch-kmp A 109 tokens
- Skill matrixscan-batch-rn A 76 tokens
- Skill matrixscan-batch-web A 85 tokens
- Skill matrixscan-count-capacitor A 102 tokens
- Skill matrixscan-count-flutter A 78 tokens
- Skill matrixscan-count-rn A 88 tokens
- Skill matrixscan-find-kmp A 103 tokens
- Skill parser-kmp A 113 tokens
- Skill sparkscan-rn A 65 tokens
- Skill barcode-capture-ios A 88 tokens
- Skill barcode-capture-web A 101 tokens
- Skill label-capture-web A 85 tokens
- Skill matrixscan-ar-android A 66 tokens
- Skill matrixscan-ar-capacitor A 85 tokens
- Skill matrixscan-ar-ios A 85 tokens
- Skill matrixscan-batch-android A 66 tokens
- Skill matrixscan-pick-ios A 84 tokens
- Skill matrixscan-pick-kmp A 99 tokens
- Skill sparkscan-capacitor A 93 tokens
- Skill sparkscan-flutter A 66 tokens
- Skill sparkscan-web A 111 tokens
- Skill matrixscan-ar-annotation-ios A 100 tokens
- Skill sparkscan-android A 57 tokens
- Skill sparkscan-ios A 54 tokens
- Skill matrixscan-ar-highlight-ios A 57 tokens
- Skill sparkscan-cordova A 94 tokens
- MCP server scandit A not measured
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 16d ago Changed · +1 lines bb4be107975f
- 18d ago Changed · +1 lines 3859f050bf91
- 1mo ago First seen · 41 lines scan A 7e14d69780fb
scandit-sdk is a plugin published in the GitHub repository Scandit/skills (20 stars, last pushed 3d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
switchbot
Control SwitchBot smart-home devices from Gemini CLI via MCP using the default tool profile and policy-based safety gates.
drone-cv-expert
Expert in drone systems, computer vision, and autonomous navigation. Specializes in flight control, SLAM, object detection, sensor fusion, and path planning. Activate on "drone", "UAV", "SLAM", "visual odometry", "PID control", "MAVLink", "Pixhawk", "path planning", "A", "RRT", "EKF", "sensor fusion", "optical flow".
r2g-skills
RTL-to-GDS-to-Graph skill collection. eda-install detects the machine and installs + verifies the open-source EDA toolchain (with a no-sudo conda path). signoff-loop drives an open-source EDA flow (Yosys + OpenROAD-flow-scripts + KLayout + Magic + Netgen + OpenRCX) from a spec or RTL to signed-off GDSII (DRC, LVS…
vmware-privateai
VMware Private AI (NVIDIA): GPU inventory, vGPU profiles, utilization, model serving — 18 tools.
torch-air marketplace
Torch Accelerator Integration Readiness — evaluate how well a hardware accelerator integrates with PyTorch.
visionclaude
VisionClaude — Let Claude see the world through your eyes. Camera + voice + Meta Ray-Ban glasses bridge for Claude Code via iOS app.