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 osama-raddad/FireCrasher --skill report-crashesgit clone --depth 1 https://github.com/osama-raddad/FireCrasherWrote 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/osama-raddad/firecrasher/report-crashes)<a href="https://agentmods.dev/skills/osama-raddad/firecrasher/report-crashes"><img src="https://agentmods.dev/badge/skills/osama-raddad/firecrasher/report-crashes/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/osama-raddad/firecrasher/report-crashes"><img src="https://agentmods.dev/badge/skills/osama-raddad/firecrasher/report-crashes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00386 |
| Opus 5 | $0.00028 | $0.00193 |
| Sonnet 5 | $0.00011 | $0.00077 |
| Haiku 4.5 | $0.00006 | $0.00039 |
Grade A, and why
report-crashes 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 10d 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
Report crashes while recovering
FireCrasher keeps the app alive, but you still want every crash recorded.
The onCrash handler gives you the throwable before recovery runs — log it
there, then call recover(). Because the app survives, these arrive at your
reporter as non-fatal / handled exceptions, not fatal crashes.
Log, then recover
installFireCrasher {
onCrash {
// 1. Report first, so nothing is lost if recovery itself struggles.
FirebaseCrashlytics.getInstance().recordException(throwable) // or Sentry.captureException(throwable)
// 2. Then recover.
recover()
}
}
The order matters: report before recover() so the report is captured even
if a subsequent recovery attempt kills the process.
Add context
retryCount (in onCrash scope) tells you how many times FireCrasher has
already tried to recover this crash — useful signal on a report:
onCrash {
FirebaseCrashlytics.getInstance().apply {
setCustomKey("firecrasher_retry", retryCount)
recordException(throwable)
}
recover()
}
Don't forget out-of-process deaths
onCrash only sees JVM exceptions on threads FireCrasher controls. Native
crashes and ANRs never reach it — report those separately via the
detect-native-crashes-and-anrs skill (onPreviousProcessExit).
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.
- 10d ago First seen · 50 lines · 55 tokens per session scan A fc723e7a84f7
report-crashes is a skill published in the GitHub repository osama-raddad/FireCrasher (148 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 386 once invoked, about $0.0003 per session on Opus 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
argent-metro-debugger
Debug a JS runtime via CDP using argent debugger tools. Primary path is React Native via Metro (iOS / Android / Vega); a subset of the tools (debugger-connect, debugger-status, debugger-evaluate, debugger-log-registry) also drive a Chromium (CDP) app's renderer (an Electron app, or any Chromium browser exposing CDP)…
argent-react-native-optimization
Optimizes a React Native app by profiling first to find real bottlenecks, then sweeping for mechanical issues. Entry-point for all performance work. Use when the app feels slow, user asks to optimize, fix re-renders, reduce jank, or improve startup. Delegates to argent-react-native-profiler for measurement.
argent-native-profiler
Native profiling for CPU hotspots, UI hangs, memory issues. iOS via xctrace; Android via Perfetto. Use when diagnosing native-level performance issues.
compose-performance
Use when investigating Jetpack Compose recomposition cost, compiler stability reports, skippability, unstable parameters, frame-rate State reads, cross-phase snapshot back-writing, or @ReadOnlyComposable contracts.
Debroid CLI Debugger
Orchestrate headless Android debugging via JDWP. ACTIVATE this skill whenever asked to debug an Android application, set line or exception breakpoints, inspect runtime variables or Jetpack Compose state, step through execution, evaluate live expressions, watch fields, or diagnose runtime crashes.
maui-performance
Fix measurable MAUI performance issues. USE FOR: maui profile startup, Release/physical-device measurements, janky CollectionView, compiled bindings, oversized images, MauiImage BaseSize, thumbnail decoding, trim/NativeAOT regressions, IL2026, source-generated serializers, linker validation. DO NOT USE FOR: generic UI…