debug

debug is a skill for Claude Code from JubaKitiashvili/everything-react-native-expo. It costs 13 tokens per session (447 once invoked), scanned A, original, MIT.

A structured bug-investigation workflow for React Native apps that uses performance analysis to trace problems from reproduction to a likely cause.

In plain words
What is it for?
It is for investigating issues such as slow responses, incorrect data, broken navigation, failed API calls, crashes, and platform-specific bugs.
Why use it?
It gives developers a consistent way to narrow down whether a problem involves crashes, rendering, state, navigation, performance, networking, or native code.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the erne-universal plugin — 45 skills, 12 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 skills/jubakitiashvili/everything-react-native-expo/debug
Any agent
npx skills add JubaKitiashvili/everything-react-native-expo --skill debug
Clone the repo
git clone --depth 1 https://github.com/JubaKitiashvili/everything-react-native-expo

Made for: Claude Code.

Or install erne-universal, the plugin that ships this one along with the rest of its 45 skills, 12 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 debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/jubakitiashvili/everything-react-native-expo/debug.svg)](https://agentmods.dev/skills/jubakitiashvili/everything-react-native-expo/debug)
Your own site
<a href="https://agentmods.dev/skills/jubakitiashvili/everything-react-native-expo/debug"><img src="https://agentmods.dev/badge/skills/jubakitiashvili/everything-react-native-expo/debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 447 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 5.1 $0.00013 $0.00447
Opus 5 $0.00006 $0.00224
Sonnet 5 $0.00003 $0.00089
Haiku 4.5 $0.00001 $0.00045

Measured 6d ago against content hash 0ff9121f7a6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

debug 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/debug/SKILL.md · 75 lines

What it actually says

/debug — Systematic Diagnosis

You are executing the /debug command. Use the performance-profiler agent for systematic bug diagnosis.

Process

Step 1: Reproduce

Define exact reproduction steps:

  1. Starting state
  2. Actions taken
  3. Expected behavior
  4. Actual behavior
  5. Environment (device, OS, Expo SDK version)

Step 2: Classify the Bug

Category Indicators First Check
Crash App terminates Check Metro logs, Hermes stack trace
Render Visual glitch, wrong layout Check component tree, re-render count
State Wrong data displayed Check Zustand store, TanStack Query cache
Navigation Wrong screen, broken back Check Expo Router history, params
Performance Jank, slow response Check FPS, bundle size, memory
Network Failed API calls Check request/response, auth tokens
Native Platform-specific issue Check native logs (Xcode/Logcat)

Step 3: Investigate

JavaScript layer:

# Check Metro bundler logs
# Search for errors/warnings in console output
# Add strategic console.log at suspected points

React layer:

  • Component re-render tracking (React DevTools)
  • Props/state inspection
  • Effect dependency analysis

Native layer (if agent-device available):

  • Screenshot current state
  • Navigate through repro steps visually
  • Capture native crash logs

Step 4: Fix & Verify

  1. Identify root cause
  2. Implement minimal fix
  3. Verify fix resolves the issue
  4. Check for regression (run related tests)
  5. Document what caused it and why

Output

## Bug Report

### Summary
[One-line description]

### Root Cause
[Technical explanation]

### Fix Applied
[Files changed with explanation]

### Verification
[Steps taken to verify fix]
[Test results]
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. 6d ago First seen · 75 lines · 13 tokens per session scan A 0ff9121f7a6c

Subscribe to this mod's changes

debug is a skill published in the GitHub repository JubaKitiashvili/everything-react-native-expo (44 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 447 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 2026-08-30.

Related

Other skills, from other repositories