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/nylo-core/claude-codeWrote 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/nylo-core/claude-code/claude-code)<a href="https://agentmods.dev/plugins/nylo-core/claude-code/claude-code"><img src="https://agentmods.dev/badge/plugins/nylo-core/claude-code/claude-code/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/nylo-core/claude-code/claude-code"><img src="https://agentmods.dev/badge/plugins/nylo-core/claude-code/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
nylo-claude-code 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 1mo 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": "nylo-claude-code",
"version": "1.2.1",
"description": "20 skills (Nylo framework + Flutter platform) and 3 agents for Flutter/Nylo development",
"author": {
"name": "Nylo",
"email": "[email protected]"
},
"homepage": "https://github.com/nylo-core/claude-code",
"repository": "https://github.com/nylo-core/claude-code",
"license": "MIT",
"keywords": ["flutter", "nylo", "mobile", "dart", "ios", "android"],
"agents": [
"./agents/nylo-developer.md",
"./agents/nylo-code-reviewer.md",
"./agents/nylo-v6-to-v7-migrator.md"
]
}
What it installs
The manifest is a name and a version. 21 skills, 3 agents travel with it, and installing the plugin installs all of them — 2,108 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill flutter-app-icons A 38 tokens
- Skill flutter-permissions A 51 tokens
- Skill flutter-signing A 46 tokens
- Skill nylo-app-setup A 47 tokens
- Skill nylo-forms A 53 tokens
- Skill nylo-networking A 48 tokens
- Skill nylo-notifications A 39 tokens
- Skill nylo-routing A 54 tokens
- Skill nylo-storage A 53 tokens
- Skill nylo-widgets A 70 tokens
- Skill flutter-app-config A 40 tokens
- Skill flutter-versioning A 44 tokens
- Skill nylo-auth A 44 tokens
- Skill nylo-localization A 62 tokens
- Skill nylo-state-management A 56 tokens
- Skill nylo-testing A 49 tokens
- Skill nylo-themes A 52 tokens
- Skill mobile-design A 56 tokens
- Skill nylo-v6-to-v7-migration A 36 tokens
- Skill nylo-dev A 26 tokens
- Skill flutter-release C 45 tokens
- Agent nylo-v6-to-v7-migrator A 316 tokens
- Agent nylo-code-reviewer A 336 tokens
- Agent nylo-developer A 447 tokens
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.
- 1mo ago First seen · 19 lines scan A af6003ca1737
nylo-claude-code is a plugin published in the GitHub repository nylo-core/claude-code (4 stars, last pushed 6mo 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
flutter-ai-skills
Flutter, Dart, and Firebase skills sourced only from official documentation.
flutter-mcp-toolkit
Flutter MCP toolkit: inspect and drive debug apps (semantic snapshot, tap, hot-reload) and register custom MCP tools and resources at runtime from your Flutter app or game via mcptoolkit — closed agent feedback loop. Bundles skills, subagent, and MCP server registration.
building-flutter-apps
Flutter app architecture and Windows installer delivery skill: Riverpod 3 codegen, Freezed sealed classes, GoRouter typed-route SSOT, Hive CE persistence, privacy-safe Crashlytics/Sentry reporting, gen-l10n, and verify-before-publish Inno pipelines. Pairs flutterskilllints analyzer enforcement with Dart Decimate code.
building-flutter-apps marketplace
Plugin marketplace listing 1 plugin: building-flutter-apps.
cloudx
Integrate and audit the CloudX SDK in publisher apps. Facts are fetched live from docs.cloudx.io; this plugin ships the workflow and real-world install playbooks.
maestro-testing
Generate and manage Maestro test flows for mobile (Android, iOS) and web apps. Covers React Native, Expo, Flutter, Swift, Kotlin, Jetpack Compose, SwiftUI, UIKit, Capacitor, Ionic, and web desktop testing.