NutriSport: Agent for Claude Code

.claude/agents/crash-analyzer.md

crash-analyzer is an agent for Claude Code from satanyakiv/NutriSport. It costs 0 tokens per session (1,172 once invoked), scanned A, original, MIT.

A read-only agent that analyzes Tracey crash dump files, which are JSON records of app crashes and nearby events.

In plain words
What is it for?
It parses crash details, traces stack frames to source files, correlates recent app events, identifies the affected architectural layer, and recommends fixes; code changes require permission.
Why use it?
It turns raw crash data into a structured report and avoids changing code before the cause has been reviewed.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is satanyakiv/NutriSport's own configuration. It tells Claude Code how to work on NutriSport itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NutriSport configures →

Reuse

Borrowing it

Nothing to install: this file belongs to satanyakiv/NutriSport. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/satanyakiv/NutriSport/main/.claude/agents/crash-analyzer.md
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 crash-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/satanyakiv/nutrisport/crash-analyzer/github.svg)](https://agentmods.dev/agents/satanyakiv/nutrisport/crash-analyzer)
Your own site
<a href="https://agentmods.dev/agents/satanyakiv/nutrisport/crash-analyzer"><img src="https://agentmods.dev/badge/agents/satanyakiv/nutrisport/crash-analyzer/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.

agentmods 80×15 button for crash-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/agents/satanyakiv/nutrisport/crash-analyzer"><img src="https://agentmods.dev/badge/agents/satanyakiv/nutrisport/crash-analyzer.svg" alt="Reviewed on agentmods" width="80" 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 1,172 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.01172
Opus 5 $0.00000 $0.00586
Sonnet 5 $0.00000 $0.00234
Haiku 4.5 $0.00000 $0.00117

Measured 8d ago against content hash bedb43d526e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

crash-analyzer 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 8d 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/agents/crash-analyzer.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crash Analyzer Agent

Automatic Tracey crash dump analysis. Works read-only, generates a structured report, patches only with permission.

Operating Mode

  1. Analysis — dump parsing, code tracing, event correlation (read-only)
  2. Report — structured markdown with severity, file:line references, recommendations
  3. Patch — fixes only with explicit user permission

Never make changes without permission. Report first, then ask.

Input

Path to a .json Tracey dump file.

Step 1 — Parse Dump

Read the JSON file. Extract:

  • crash object: exception class, stacktrace, timestamp
  • events array: last N events before the crash
  • device: platform (android/ios), OS version, app version
  • sessionId, isCrashPayload

If the file is not found — ask for the path. If it is not JSON or not Tracey format — notify the user.

Step 2 — Stacktrace Analysis

For each frame in the stacktrace:

  • Glob/Grep to the source file
  • Read the file at the corresponding lines
  • Determine the module and architectural layer:
    • com.nutrisport.shared.domain:domain
    • com.nutrisport.shared.util:shared:utils
    • com.nutrisport.network:network
    • com.nutrisport.cart:feature:home:cart
    • com.nutrisport.navigation:navigation
  • Record the crash location: {file}:{line} in which module

Step 3 — Event Correlation

For each event from the dump events:

Event Type How to correlate Where to look
SCREEN Destination in NavGraph.kt navigation/.../NavGraph.kt
CLICK/TAP Screen composable for active route feature/{screen}/...Screen.kt
LOG Grep for breadcrumb text ViewModels in feature modules
FOREGROUND/BACKGROUND Lifecycle event Application / Activity
CRASH Stacktrace mapping Step 2

Read the full file on GitHub · 148 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. 8d ago First seen · 148 lines · 0 tokens per session scan A bedb43d526e2

Subscribe to this mod's changes

crash-analyzer is an agent 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 1,172 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.