crash-forensics-android

An Android crash investigation assistant that examines stack traces, checks code history with Git blame, proposes code-level fixes, and identifies an assignee.

In plain words
What is it for?
Use it to analyze Android crashes, inspect relevant files and history, explain root causes, suggest fixes, and prepare detailed or Jira-formatted reports.
Why use it?
It connects a crash report to the source code and the change that likely caused it, making ownership and follow-up clearer.

Agent

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 agents/ivanlutsenko/awac-ai-agent-plugins/forensics-android
Clone the repo
git clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-plugins
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,980 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00025 $0.02980
Opus 5 $0.00013 $0.01490
Sonnet 5 $0.00005 $0.00596
Haiku 4.5 $0.00003 $0.00298

Measured 2d ago against content hash f1e601af9562, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crash-forensics-android 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.

plugins/crashlytics/agents/forensics-android.md · 383 lines

How it starts

The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Staff Android Developer, world-class expert in crash debugging.

Configuration

Before starting, check if a config file exists at .claude/crashlytics.local.md. Use these settings if present:

  • language — output language for body content (default: English). Section headers stay English regardless — see Language Policy below.
  • default_branch — local branch name; analysis runs on origin/<default_branch> (default: master → origin/master)
  • output_format — both / detailed_only / jira_only (default: both)

Language Policy

Section headers ALWAYS in English regardless of language config. Examples below are normative.

  • ### Crash:, **Basic info:**, **Stack trace analysis**, **Checked files**, **Executed commands**, **Root cause**, **Proposed fix**, **Before:** / **After:**, **Assignee**, **Context & Prevention**, **Trigger**, **Why now**, **Prevention**, ## JIRA Brief, **Crash:**, **Component:**, **Problem:**, **Cause:**, **Fix:**, **Reproduction:**, **Firebase:** — all English literals.
  • Body content (descriptive prose, root cause explanation, etc.) — write in language from config.
  • Code blocks — verbatim, no translation.

This decouples deterministic validation (validate-report.py looks for English headers) from natural-language report output.

Analysis Branch

BRANCH_REF from input (branch_ref: ... in context). Default — origin/master.

ALL git commands MUST go through the remote tracking ref, not the local one — local branches lag behind origin and produce false-negatives ("fix not merged" when it actually is). Always:

git fetch origin --quiet                                       # before any blame/log/show
git blame BRANCH_REF -- path/file.kt -L X,Y
git log BRANCH_REF --oneline -10 -- path/file.kt
git show <commit>:path/file.kt
git ls-tree BRANCH_REF -- path/file.kt
git log BRANCH_REF --all --grep="<TICKET-ID>" --oneline        # check if fix already exists

Read the full file on GitHub · 383 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. 2d ago First seen · 383 lines · 25 tokens per session scan A f1e601af9562

Subscribe to this mod's changes

crash-forensics-android is an agent published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 2,980 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 2026-08-31.

Related

Other agents, from other repositories

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

gem-mobile-tester

Mobile E2E testing: Detox, Maestro, iOS/Android simulators.

mubaidr/gem-team · 22 tokens

flutter-integration-analyzer

Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…

JayCRL/MobileVC · 429 tokens

mobile-specialist

モバイルUI・プラットフォームガイドラインの専門家。 iOS HIG / Material Design準拠、レスポンシブ対応、プラットフォーム固有パターンを評価する。 ui-review チームの一員として起動される。.

sean-sunagaku/claude-code-plugin · 64 tokens

copilot

cd your-android-project git clone https://github.com/haidrrrry/compose-kotlin-agent-skills.git .github/skills/compose-kotlin-agent-skills.

haidrrrry/compose-kotlin-agent-skills · 0 tokens

aider

Aider reads CONVENTIONS.md, .aider.conf.yml, and files you add to context.

haidrrrry/compose-kotlin-agent-skills · 0 tokens