Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add IvanLutsenko/awac-ai-agent-plugins/plugin install crashlyticsWrote 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/ivanlutsenko/awac-ai-agent-plugins/crash-report-ios)<a href="https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/crash-report-ios"><img src="https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/crash-report-ios.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01981 |
| Opus 5 | $0.00000 | $0.00991 |
| Sonnet 5 | $0.00000 | $0.00396 |
| Haiku 4.5 | $0.00000 | $0.00198 |
Grade B, and why
crash-report-ios scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Bash: mkdir -p .claude && cat <<'EOF' > .claude/crashlytics.local.md Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(${CLAUDE_PLUGIN_ROOT}/scripts/*), Bash(python3 ${CLAUDE_PLUGIN_ROOT}/scripts/*), Bash(git log:*), Bash(git blame:*), Bash(git diff:*), Bash(git show:*), Bash(git fetch:*), Bash(git ls-tree:*), Bash(gi This is a copy
91% identical to crash-report-android — 42 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS Crash Analysis - Multi-Agent Edition
Analyze crash errors from Firebase Crashlytics using specialized agents.
Configuration
Before starting, check if a config file exists at .claude/crashlytics.local.md.
If it exists, read and use these settings:
language— output language for body content (default: English). Section headers stay English.default_branch— local branch name; analysis runs onorigin/<default_branch>(default: master)forensics_model— model for forensics agent (default: opus)output_format— both / detailed_only / jira_only (default: both)firebase_project_id— pre-configured project ID (skip auto-detection if set)firebase_app_id_ios— pre-configured app ID (skip auto-detection if set)
If config doesn't exist, auto-create it with defaults and continue:
Bash: mkdir -p .claude && cat <<'EOF' > .claude/crashlytics.local.md
---
language: en
default_branch: master # local branch name; plugin uses origin/<this> for git blame
default_platform: ios
forensics_model: opus
output_format: both
firebase_project_id: ""
firebase_app_id_android: ""
firebase_app_id_ios: ""
---
# Crashlytics Plugin Config
Auto-created with defaults. Run `/crash-config` to customize.
EOF
Multi-Agent Architecture
classifier-ios(Haiku) → fetcher(Haiku) → forensics-ios(Opus) → validate-report.py → output
Workflow
Prerequisites Check (cached)
Skip if .claude/crashlytics-prereqs-ok exists. Otherwise run and cache on success.
Bash: test -f .claude/crashlytics-prereqs-ok && echo "CACHED_OK"
If not cached:
Bash: ${CLAUDE_PLUGIN_ROOT}/scripts/check-prerequisites.sh
Parse: OK → pass, MISSING → show fix instruction
If ALL OK → Bash: touch .claude/crashlytics-prereqs-ok
If any MISSING → show checklist, degrade gracefully (do NOT cache)
Fix instructions: node → brew install node, firebase → npm install -g firebase-tools, firebase-auth → firebase login in terminal, python3 → brew install python3.
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.
- 7d ago First seen · 186 lines · 0 tokens per session scan B e5d9d7753ad5
crash-report-ios is a command published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,981 tokens. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). It is 91% identical to crash-report-android, differing in 42 lines, and is treated as a copy.
Other commands, from other repositories
flutter-build
Fix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.
decompile
Decompile an Android APK/XAPK/JAR/AAR and analyze its structure.
safe-decompile
Safely fingerprint and decompile an Android artifact through the sandboxed MCP server.
debug
Debug Purchasely SDK issues — diagnose blank paywalls, frozen UI, purchase failures, and more.
proguard
Command "proguard" from getsentry/cli, covering examples, compute the uuid for a proguard/r8 mapping file, output as json (includes the file path) and important notes.
xcode-build-fix
Incrementally fix Xcode build and Swift compiler errors. Parse errors, explain issues, apply fixes, verify resolution.