debugging-troubleshooting-prompt

debugging-troubleshooting-prompt is an agent for Claude Code from Rtur2003/Claude-Code-Promts-Skills. It costs 0 tokens per session (3,684 once invoked), scanned A, original, MIT.

A role prompt for systematically finding and resolving problems in production software. It uses symptoms, logs, measurements, traces, reproduction steps, and incident-response practices to investigate causes.

In plain words
What is it for?
Use it to classify incidents, collect evidence, trace requests across services, analyze logs, profile performance, reproduce failures, isolate root causes, implement fixes, and check their effects.
Why use it?
It replaces guesswork with a process for narrowing down where and why a failure occurs. It also considers the wider impact of a bug and how to verify the fix or prevent a repeat.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-code-prompts plugin — 5 skills, 39 agents, 1 hook 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 agents/rtur2003/claude-code-promts-skills/debugging-troubleshooting-prompt
Clone the repo
git clone --depth 1 https://github.com/Rtur2003/Claude-Code-Promts-Skills

Made for: Claude Code.

Or install claude-code-prompts, the plugin that ships this one along with the rest of its 5 skills, 39 agents, 1 hook.

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 debugging-troubleshooting-prompt

README.md
[![agentmods](https://agentmods.dev/badge/agents/rtur2003/claude-code-promts-skills/debugging-troubleshooting-prompt.svg)](https://agentmods.dev/agents/rtur2003/claude-code-promts-skills/debugging-troubleshooting-prompt)
Your own site
<a href="https://agentmods.dev/agents/rtur2003/claude-code-promts-skills/debugging-troubleshooting-prompt"><img src="https://agentmods.dev/badge/agents/rtur2003/claude-code-promts-skills/debugging-troubleshooting-prompt.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 3,684 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.03684
Opus 5 $0.00000 $0.01842
Sonnet 5 $0.00000 $0.00737
Haiku 4.5 $0.00000 $0.00368

Measured 2d ago against content hash 28ad6c0a14ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

debugging-troubleshooting-prompt scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -w "@/tmp/curl-format.txt" -o /dev/null -s https://api.example.com/health
prompts/english/agents/debugging-troubleshooting-prompt.md · 462 lines

How it starts

The opening of the file, as written. The whole thing — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging & Troubleshooting Specialist

Production Debugging | Performance Profiling | Incident Response

Use this when: diagnosing a production incident or a hard bug — collecting evidence, isolating the root cause, and verifying the fix. Skip to: Protocol · Phase 1: DETECT · Phase 2: EVIDENCE · Phase 3: BISECT · Remember

Role

You are a Debugging & Troubleshooting Specialist who systematically diagnoses and resolves issues in production systems. You master profiling tools, distributed tracing, log analysis, and incident response — turning chaos into clarity through methodical investigation.

Protocol: DEBUG

D → DETECT     — Identify symptoms, scope, and impact of the issue
E → EVIDENCE   — Collect logs, metrics, traces, and reproduction steps
B → BISECT     — Narrow down the root cause through systematic elimination
U → UNDERSTAND — Comprehend why the bug exists and its full blast radius
G → GUIDE      — Implement fix, verify, and prevent recurrence

Phase 1: DETECT — Issue Identification

Severity Classification

Level Impact Response Time Example
P0 — Critical Service down, data loss Immediate (< 15 min) Database corruption, auth bypass
P1 — High Major feature broken < 1 hour Payment failures, data sync broken
P2 — Medium Feature degraded < 4 hours Slow queries, intermittent errors
P3 — Low Minor issue Next sprint UI glitch, non-critical log errors

Initial Assessment Template

## Issue Report
- **Severity**: P[0-3]
- **First detected**: [timestamp]
- **Affected**: [users/services/regions]
- **Symptoms**: [what's happening]
- **Expected**: [what should happen]
- **Changed recently**: [deployments, config changes, traffic patterns]
- **Workaround**: [temporary mitigation if available]

Read the full file on GitHub · 462 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 Changed · +3 lines 28ad6c0a14ae
  2. 6d ago First seen · 459 lines · 0 tokens per session scan A 4ccf844169d7

Subscribe to this mod's changes

debugging-troubleshooting-prompt is an agent published in the GitHub repository Rtur2003/Claude-Code-Promts-Skills (50 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,684 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

qa-testing-feature

Performs QA testing on the feature implemented in the current branch. Reads specs, docs, and API docstrings, creates a QA test plan, executes tests using Playwright against a debug server, and generates a report with found issues. Use after implementing a feature to validate it meets requirements before finalizing a…

streamlit/streamlit · 67 tokens

root-cause-debugger

Use proactively when a failure must be reproduced, isolated, and causally explained before a fix is written. Do not use when the cause is already established and implementation is authorized.

zebbern/claude-code-guide · 41 tokens

code-searcher

Use for codebase analysis, forensic examination, and code mapping — locating functions, classes, and logic; security vulnerability analysis; pattern detection; architectural consistency checks; and navigable code references with exact file:line numbers. Delegate when the user needs to find where code lives, understand…

centminmod/my-claude-code-setup · 75 tokens

debugging-specialist

Systematic 4-phase debugging for complex and intermittent issues. Use when investigating bugs, tracking down race conditions, or diagnosing mysterious failures.

travisjneuman/.claude · 32 tokens

devils-advocate-agent

Challenges assumptions, tests logical chains, detects biases and fallacies, and stress-tests argument robustness at three mandatory checkpoints in the deep-research pipeline, issuing a PASS/REVISE verdict per checkpoint.

AlterLab-IEU/AlterLab-Academic-Skills · 47 tokens

alchemist

Code/data transmutation via four-stage alchemical process (nigredo/albedo/citrinitas/rubedo) with meditate/heal checkpoints.

pjt222/agent-almanac · 32 tokens