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/kobiton/automateWrote 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/kobiton/automate/gemini-extension)<a href="https://agentmods.dev/plugins/kobiton/automate/gemini-extension"><img src="https://agentmods.dev/badge/plugins/kobiton/automate/gemini-extension/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/kobiton/automate/gemini-extension"><img src="https://agentmods.dev/badge/plugins/kobiton/automate/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kobiton-automate 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 3d 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": "kobiton-automate",
"version": "1.15.0",
"description": "Connect to Kobiton mobile testing platform - manage devices, run automation suites, and view test results",
"contextFileName": "AGENTS.md",
"mcpServers": {
"kobiton": {
"httpUrl": "https://api.kobiton.com/mcp",
"headers": {
"X-AI-Tool-Name": "Gemini"
}
}
}
}
What ships with it
14 files beside gemini-extension.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.
- assets/logo.svg 6.3 KB
- scripts/build-tool-definitions.js 1.9 KB runs code
- scripts/build-tool-definitions.test.js 4.7 KB runs code
- scripts/install-cli.sh 9.7 KB runs code
- scripts/mcp-tools-dist-tag.js 1.5 KB runs code
- scripts/mcp-tools-dist-tag.test.js 3.4 KB runs code
- scripts/sync-codex-artifacts.js 5.3 KB runs code
- scripts/sync-codex-artifacts.test.js 5.9 KB runs code
- scripts/sync-version.js 4.9 KB runs code
- scripts/sync-version.test.js 7.1 KB runs code
- scripts/validate.js 8.3 KB runs code
- scripts/validate.test.js 11 KB runs code
- scripts/write-credentials.js 10.0 KB runs code
- scripts/write-credentials.test.js 10 KB runs code
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.
- 3d ago Changed 4b2a9e657850
- 6d ago Changed 388df3342e09
- 10d ago Changed 79877109c725
- 14d ago Changed b7ff5445e336
- 1mo ago First seen · 15 lines scan A 0c706acac872
kobiton-automate is a plugin published in the GitHub repository kobiton/automate (13 stars, last pushed yesterday), licensed MIT. 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 2026-09-11.
Other plugins, from other repositories
aco
Drive a live Appium session from Claude Code with the aco CLI — start/stop sessions, find elements, tap, swipe, type, screenshot, read page source, switch web contexts, and call platform mobile: extensions on iOS simulators/emulators and real devices.
serve-sim
Control and stream a running iOS, iPad, or Apple Watch Simulator with serve-sim.
apple-skills
164 Apple platform development skills across 23 categories (iOS, macOS, watchOS, visionOS): code generators, product workflow, App Store/ASO, testing and TDD, design, performance, security, and more. Surfaced as 23 category skills that route to the full library.
ios-all
All 11 iOS skills: swiftui-mvvm, uikit-mvvm, viper-uikit, tca-swiftui, swift-concurrency, gcd-operations, ios-testing, ios-security, ios-accessibility, ios-localization, ios-logging.
sdlc
Software Development Lifecycle standards and requirements for project quality, security, and compliance.
xcode-cli
Xcode CLI — Build, test, run, and manage Xcode projects from Claude Code.