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 IvanLutsenko/awac-ai-agent-pluginsnpx agentmods add plugins/ivanlutsenko/awac-ai-agent-plugins/crashlyticsgit clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-pluginsGrade A, and why
crashlytics 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 2d 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": "crashlytics",
"description": "Multi-platform crash analysis for Android & iOS with git blame forensics, code-level fixes, and deterministic quality gate. MCP-primary fetch with REST API fallback. Language-aware validator and origin/<branch> forensics.",
"version": "4.4.4",
"mcpServers": "./.mcp.json",
"author": {
"name": "Ivan Lutsenko",
"email": "[email protected]",
"url": "https://github.com/IvanLutsenko"
},
"keywords": ["crashlytics", "crash-report", "firebase", "android", "ios", "swift", "kotlin", "debugging", "git-blame", "multi-agent"],
"license": "MIT",
"commands": [
"./commands/crash-report.md",
"./commands/crash-report-android.md",
"./commands/crash-report-ios.md",
"./commands/crash-config.md",
"./commands/install-permissions.md"
],
"agents": [
"./agents/classifier-android.md",
"./agents/classifier-ios.md",
"./agents/firebase-fetcher.md",
"./agents/forensics-android.md",
"./agents/forensics-ios.md"
]
}
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.
- 2d ago First seen · 28 lines scan A 359a275c8aaa
crashlytics is a plugin published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 1mo 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
iOS plugin.
mobile-observability
Expert guidance and automation for mobile app observability: crash reporting, performance monitoring, session replay, and instrumentation for iOS, Android, React Native, and Flutter.
safe-android-reverser
Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.
erne-universal
Complete AI coding agent harness for React Native and Expo — 13 agents, 22 commands, 7 skills, 10 MCP integrations, autonomous worker mode, visual debugging, smart routing.
carloshpdoc-plugins marketplace
iOS-opinionated Claude Code workflow automation: Swift 6 migration, Apollo to native SDK removal, stacked PRs, Jira integration, Xcode build optimization.
swift-performance-pro
Performance: Instruments, SwiftUI render cost, memory and retain cycles, launch time, lists.