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.
/plugin marketplace add ShipWithAI/shipwithai-pluginsnpx agentmods add plugins/shipwithai/shipwithai-plugins/mobile-ui-harnessgit clone --depth 1 https://github.com/ShipWithAI/shipwithai-pluginsGrade A, and why
shipwithai-mobile-ui-harness 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": "shipwithai-mobile-ui-harness",
"version": "0.1.0",
"description": "Self-improving Compose Multiplatform UI harness for Claude Code. A render -> grade -> ratchet loop: inspection tests render every screen across a stress matrix, a deterministic Tier-1 asserter plus a vision evaluator grade them in a separate lane, and recurring findings ratchet into permanent gates via a compounding feedback ledger. Ships Konsist architecture rails and a setup skill that scaffolds it all into a project.",
"author": {
"name": "ShipWithAI",
"url": "https://shipwithai.io"
},
"homepage": "https://shipwithai.io/plugins/mobile-ui-harness",
"repository": "https://github.com/ShipWithAI/shipwithai-plugins",
"license": "MIT",
"keywords": ["claude-code", "compose-multiplatform", "kotlin", "android", "roborazzi", "konsist", "ui", "screenshot-testing", "evaluator", "design-review"],
"skills": [
"./skills/setup",
"./skills/mobile-design",
"./skills/konsist-architecture-tests"
],
"agents": [
"./agents/mobile-design-evaluator.md"
]
}
What it installs
The manifest is a name and a version. 2 skills, 3 commands, 1 agent travel with it, and installing the plugin installs all of them — 396 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 First seen · 22 lines scan A 39b123250630
shipwithai-mobile-ui-harness is a plugin published in the GitHub repository ShipWithAI/shipwithai-plugins (10 stars, last pushed 21d ago), 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 2026-08-31.
Other plugins, from other repositories
maestro-mobile-validator
iOS and Android mobile app validation via Maestro flows with simulator management and CI patterns.
rn-agents-kit
Audit-first agent skills for React Native maintenance: code-quality audit, New Architecture readiness, asset hygiene, project snapshot, device screen capture, and Metro console capture.
swift
Swift programming language utilities and migration tools for Claude Code.
ios-agent-skills
Production-tested iOS Agent Skills — 11 enterprise-grade skills for architecture, concurrency, testing, security, accessibility, localization, and logging.
swiftui
SwiftUI patterns and critique for iOS, macOS, and visionOS apps.
ios-skills
200+ iOS/Swift/Xcode skills with phase-aware routing. Full lifecycle: ideation, design, develop, test, deploy, iterate.