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 kobiton/automate --skill create-test-rungit 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/skills/kobiton/automate/create-test-run)<a href="https://agentmods.dev/skills/kobiton/automate/create-test-run"><img src="https://agentmods.dev/badge/skills/kobiton/automate/create-test-run/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/kobiton/automate/create-test-run"><img src="https://agentmods.dev/badge/skills/kobiton/automate/create-test-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 115 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 115 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00207 | $0.03103 |
| Opus 5.5 | $0.00083 | $0.01241 |
| Sonnet 5.5 | $0.00041 | $0.00621 |
| Haiku 4.5 | $0.00021 | $0.00310 |
Grade A, and why
create-test-run 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prerequisites
Needs only an authenticated Kobiton MCP connection — no local filesystem, no credentials file, no
binary, no shell. It is the plugin's only pure-MCP skill, so it is the only one that works where the
host supplies nothing else. The monitoring hand-off in Step 5 is the exception: monitor-test-run
runs a local poller, so where you can't run a local command at all, create the run and report its id
instead of offering to watch it (Step 5 carries the wording). Where you can, hand off and let that
skill check its own credentials and streaming options — it degrades rather than refusing. See the Skill
compatibility matrix in CLAUDE.md.
Overview
Turn a "run this" request into a created test run with as little friction as the user wants, then offer to watch it. Two phases:
- Build + confirm the run. Resolve what to run (test case or suite), on which devices, with what app — filling any unspecified field with a documented default — then show a one-screen summary and create on confirmation.
- Offer monitoring once. After creation, present the monitor choice in a
single prompt and delegate to
monitor-test-runif the user wants it.
Tool naming. Kobiton MCP tools are referenced by bare name (
createTestRun,getOrgSettings,listDevices,getTestCase,getTestSuite). The host resolves the prefix (mcp__plugin_automate_kobiton__createTestRun,mcp__kobiton__createTestRun, etc.).
userIntent. Optional: pass one sentence on why when the tool name and arguments show what the call does but not why (e.g.terminateSession,deleteTestCase); omit it when the reason is obvious from the call (e.g.listDevices,getSession).
Inputs
| Input | Required | Notes |
|---|---|---|
| test case id or test suite id | one of | A test case id → TEST_CASE selection; a suite id → TEST_SUITE. If the user named neither, ask for it (it's the one thing with no sensible default). |
| device count / specific devices | no | Default: 1 device matching the test case/suite platform. The user may say "3 devices", name models, or give UDIDs. |
| run name / app version / allocation | no | All defaulted (see Step 2). |
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.
- 4d ago Changed · +5 lines 7592ee5c283f
- 1mo ago Changed · +1 lines 90deba61a77f
- 1mo ago First seen · 208 lines · 207 tokens per session scan A 1f7f858f1e0d
create-test-run is a skill published in the GitHub repository kobiton/automate (14 stars, last pushed 5d ago), licensed MIT. It adds 207 tokens to every session and 3,103 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
finalrun-use-cli
Use the published FinalRun CLI to install, configure, validate, run, troubleshoot, and inspect reports for repo-local mobile test workspaces. Trigger this skill for requests involving finalrun, check, test, suite, doctor, runs, start-server.
Appium Mobile Testing
Mobile application testing skill using Appium for iOS and Android, covering device capabilities, selectors, gestures, and cross-platform testing strategies.
noqa-testing
Use this skill when the user wants to boot and interact with iOS or Android devices/simulators — inspect the screen, execute actions, generate or edit test cases, or run UI tests via the noqa platform.
mobiloop-mobile-qa
Test mobile apps with MobiLoop MCP, collect device evidence, and fix and retest confirmed failures within the user's scope. Use for Flutter, React Native, Android, or iOS QA on an emulator, simulator, or device, including relevant mobile security checks.
aco
Drive a live Appium session from the shell with the aco CLI. Use when the user wants to interact with a running mobile app on an iOS simulator, Android emulator, or connected real device — tap, swipe, type, screenshot, read the screen/page source, find UI elements, switch to a WebView context, or call iOS/Android…
mobile-tester
You are the Mobile Tester Specialist. You connect to real Android/iOS devices and write, execute, and report on mobile UI test cases. You master THREE testing modalities.