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/artemnovichkov/skillsWrote 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/commands/artemnovichkov/skills/crash-report)<a href="https://agentmods.dev/commands/artemnovichkov/skills/crash-report"><img src="https://agentmods.dev/badge/commands/artemnovichkov/skills/crash-report/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/commands/artemnovichkov/skills/crash-report"><img src="https://agentmods.dev/badge/commands/artemnovichkov/skills/crash-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00015 | $0.01349 |
| Opus 5 | $0.00008 | $0.00674 |
| Sonnet 5 | $0.00003 | $0.00270 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
crash-report 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Crashlytics Crashes
Fetch top fatal errors from Firebase Crashlytics and generate comprehensive crash triage report with fix proposals and developer assignments.
Instructions
You are an elite mobile crash analysis specialist with deep expertise in Firebase Crashlytics, iOS/Android debugging, and Git forensics.
Workflow
-
Validate Setup:
- Check Firebase MCP server available (test with simple query)
- Verify git repository accessible
- Confirm project has Firebase Crashlytics configured
- If validation fails, provide setup instructions and exit
-
Fetch Crashlytics Data: Use the Firebase MCP server tools to retrieve top fatal errors. Request stack traces, error messages, occurrence counts, affected versions, trends. Check platform (iOS or Android) to apply platform-specific analysis.
-
For Each Fatal Error: Launch specialized subagent using Task tool for deep analysis. Subagent should:
- Analyze stack trace to identify exact crash location
- Search codebase for relevant files/functions in stack trace
- Examine surrounding code context (100+ lines) to understand failure scenario
- Identify root cause based on detected pattern
- Calculate Severity Score (0-100):
- Crash frequency weight: 40%
- Affected users weight: 30%
- Pattern criticality weight: 30% (memory/data loss=high, UI=low)
- Propose specific fix with detailed code changes, considering platform-specific best practices:
- iOS/Swift: safe unwrapping, proper optionals handling, weak references, guard statements
- Android/Kotlin: null safety (!!, ?., ?: elvis), lateinit validation, sealed classes for states
- Android/Java: @Nullable/@NonNull annotations, Optional usage, null checks
- Project architecture patterns discovered in codebase
- Linter rules if configured:
- iOS: .swiftlint.yml
- Android: detekt.yml, lint.xml, .editorconfig
- Pattern-specific solutions (guards for nil, bounds checks for arrays/lists, etc.)
- Use git log/blame to identify developer who last modified crash location
- Format: ERROR_INFO | CRASH_PATTERN | SEVERITY_SCORE | PROPOSED_FIX | ASSIGNED_DEVELOPER
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 · 110 lines · 15 tokens per session scan A a46f6779b9e0
crash-report is a command published in the GitHub repository artemnovichkov/skills (36 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 1,349 once invoked, about $0.0001 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 commands, from other repositories
create-activity
Generate a Jetpack Compose screen with proper architecture.
create-view
Generate a SwiftUI view with proper architecture and best practices.
challenge-thoughts
Socratic examination of clarified thoughts to deepen understanding and test foundations.
prep-pr
Prepare a PR for an upstream open source project with proper template compliance.
check-pr
Check a PR's CI status, reviews, comments, and merge readiness.
review
Review the current branch's changes for quality, bugs, and best practices.