crash-report

crash-report is a command for coding agents from IvanLutsenko/awac-ai-agent-plugins. It costs 32 tokens per session (1,968 once invoked), scanned B, original, MIT.

A command that investigates application crashes reported by Firebase Crashlytics, a service that collects crash reports from Android and iOS apps.

In plain words
What is it for?
Use it to analyze Android or iOS crashes, connect findings to the relevant code branch, and produce a crash-analysis report.
Why use it?
It gathers the project settings and platform details needed to analyze crashes consistently, instead of making developers inspect reports manually.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the crashlytics plugin — 10 skills, 5 commands, 5 agents shipped together

Install

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.

agentmods
npx agentmods add commands/ivanlutsenko/awac-ai-agent-plugins/crash-report
Clone the repo
git clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-plugins

Or install crashlytics, the plugin that ships this one along with the rest of its 10 skills, 5 commands, 5 agents.

Wrote 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.

agentmods badge for crash-report

README.md
[![agentmods](https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/crash-report.svg)](https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/crash-report)
Your own site
<a href="https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/crash-report"><img src="https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/crash-report.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,968 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.01968
Opus 5 $0.00016 $0.00984
Sonnet 5 $0.00006 $0.00394
Haiku 4.5 $0.00003 $0.00197

Measured 5d ago against content hash c68f8382c317, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

crash-report 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 5d 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
plugins/crashlytics/commands/crash-report.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crash Analysis

Unified crash analysis command. Reads default_platform from config and calls the right agents.

Step 0: Config + Platform

1. Check config:
   Glob: .claude/crashlytics.local.md

2. If config exists → Read it, parse YAML frontmatter.
   Set PLATFORM = default_platform (android | ios)

3. If config NOT found → auto-create with defaults:
   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: android
   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

   Set PLATFORM = android
   Inform user: "Config created at `.claude/crashlytics.local.md` (defaults: android, origin/master, opus). Run `/crash-config` to customize."

Config values used throughout:

  • PLATFORM → which agents to call + console URL format
  • default_branch → local branch name; analysis runs on origin/<default_branch>
  • forensics_model → model for forensics agent (default: opus)
  • output_format → both / detailed_only / jira_only
  • firebase_project_id, firebase_app_id_{PLATFORM} → skip auto-detect if set

Step 0.5: 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 output: OK → pass, MISSING → fail with 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.

Read the full file on GitHub · 178 lines

Changes

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.

  1. 5d ago First seen · 178 lines · 32 tokens per session scan B c68f8382c317

Subscribe to this mod's changes

crash-report is a command published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 1,968 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.