debug-crash

debug-crash is a command for Claude Code from satanyakiv/NutriSport. It costs 0 tokens per session (696 once invoked), scanned A, original, MIT.

A read-only crash-investigation command for Tracey JSON replay files, which contain crash details and a timeline of app events.

In plain words
What is it for?
It helps trace crashes to source files, navigation, screens, ViewModels, or network and data-mapping layers, then classify the likely root cause and fix layer.
Why use it?
It connects the crash stack trace with recent screens, gestures, logs, device information, and the app’s architecture so the likely cause can be located.

Command for Claude Code

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/satanyakiv/nutrisport/debug-crash
Clone the repo
git clone --depth 1 https://github.com/satanyakiv/NutriSport

Made for: Claude Code.

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 debug-crash

README.md
[![agentmods](https://agentmods.dev/badge/commands/satanyakiv/nutrisport/debug-crash.svg)](https://agentmods.dev/commands/satanyakiv/nutrisport/debug-crash)
Your own site
<a href="https://agentmods.dev/commands/satanyakiv/nutrisport/debug-crash"><img src="https://agentmods.dev/badge/commands/satanyakiv/nutrisport/debug-crash.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 696 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 $0.00000 $0.00696
Opus 5 $0.00000 $0.00348
Sonnet 5 $0.00000 $0.00139
Haiku 4.5 $0.00000 $0.00070

Measured 5d ago against content hash 3017d9bef223, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-crash 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 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.

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.

.claude/commands/debug-crash.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read .claude/rules/architecture.md, .claude/rules/error-handling.md

Crash Dump

$ARGUMENTS

Process

  1. PARSE — read the Tracey JSON replay file:

    • Crash event + stacktrace
    • Last 10-15 events before the crash (timeline)
    • Screen transitions (SCREEN events), gesture events (CLICK/SWIPE/SCROLL), breadcrumbs (LOG)
    • Device info, session ID, isCrashPayload flag
  2. CORRELATE — for each stacktrace frame:

    • Glob/Grep to source file + read relevant lines
    • Determine module + architectural layer (domain/network/feature/navigation)
    • For SCREEN events → find destination in navigation/.../NavGraph.kt
    • For LOG events → find Tracey.log() call in ViewModel
    • For gesture events → find the Screen composable that was active
  3. ANALYZE — root cause classification:

    Category Indicators Fix Layer
    Null safety NPE in stacktrace Domain (NullSafety.kt) or Mapper
    Network AppError.Network :network repository
    State race concurrent state entries ViewModel (mutex/conflate)
    Navigation IllegalArgumentException Screen.kt / NavGraph.kt
    Auth AppError.Unauthorized :network auth check
    Data mapping ClassCast/Serialization Mapper in :network or feature
    Lifecycle IllegalState after onDestroy ViewModel scope/Flow collection
  4. PRESENT findings:

    User Journey (from dump)

    # Time Event Detail Code Path

    Root Cause

    Category + explanation with file:line references

    Proposed Fix

    Minimal diff in correct architectural layer

    Wait for "go".

  5. FIX — delegate to /fix with identified bug: /fix <root cause description from analysis>

Bonus

If dump contains Tracey-generated Kotlin test (via captureAndExportTest()), show it as a ready-to-use regression test.

Dump Location

Default: ./tracey-dumps/replay_<sessionId>.json Pull from device: adb pull /data/data/com.portfolio.nutrisport.debug/files/tracey/ ./tracey-dumps/

Read the full file on GitHub · 80 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 · 80 lines · 0 tokens per session scan A 3017d9bef223

Subscribe to this mod's changes

debug-crash is a command published in the GitHub repository satanyakiv/NutriSport (11 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 696 tokens. 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.