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/aaronbassett/agent-foundryWrote 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/aaronbassett/agent-foundry/flutter-core)<a href="https://agentmods.dev/plugins/aaronbassett/agent-foundry/flutter-core"><img src="https://agentmods.dev/badge/plugins/aaronbassett/agent-foundry/flutter-core/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/aaronbassett/agent-foundry/flutter-core"><img src="https://agentmods.dev/badge/plugins/aaronbassett/agent-foundry/flutter-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
flutter-core 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": "flutter-core",
"version": "0.7.1",
"description": "Comprehensive Flutter and Dart development toolkit providing expert guidance on UI/UX, architecture, state management, testing, performance, deployment, and backend integration with ServerPod",
"author": {
"name": "Aaron Bassett",
"email": "[email protected]",
"url": "https://aaronbassett.com"
},
"homepage": "https://github.com/aaronbassett/agent-foundry",
"repository": "https://github.com/aaronbassett/agent-foundry/tree/main/plugins/flutter-core",
"license": "MIT",
"keywords": [
"flutter",
"dart",
"mobile",
"ui",
"material-design",
"state-management",
"serverpod",
"testing",
"performance",
"deployment"
]
}
What it installs
The manifest is a name and a version. 3 skills, 4 commands, 5 agents, 1 MCP server travel with it, and installing the plugin installs all of them — 449 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill flutter-core:flutter-data-networking A 48 tokens
- Skill flutter-core:flutter-animations A 46 tokens
- Skill flutter-core:flutter-architecture A 50 tokens
- Command flutter-build A 22 tokens
- Command flutter-upgrade A 18 tokens
- Command flutter-analyze A 26 tokens
- Command flutter-new A 19 tokens
- Agent flutter-backend-specialist A 47 tokens
- Agent flutter-platform-engineer A 48 tokens
- Agent flutter-architect A 40 tokens
- Agent flutter-performance-expert A 45 tokens
- Agent flutter-ui-specialist A 40 tokens
- MCP server dart A not measured
What ships with it
2 files 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 · 26 lines scan A 2a6cd4acd486
flutter-core is a plugin published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 2mo 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
ios
MobiAI for iOS — simulator, build, testing, and architecture skills.
swift-performance-pro
Performance: Instruments, SwiftUI render cost, memory and retain cycles, launch time, lists.
eternal-pose
Build and evolve map-first, mobile-first travel sites from real itinerary material.
safe-android-reverser
Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.
react-native
Guides for Expo Modules API and NativeWind styling.
areclaw
Android reverse engineering and security analysis — decompile APKs, intercept traffic, run Frida scripts, scan for secrets, extract APIs, and generate OWASP-aligned security reports.