# devops-troubleshooter

This subagent investigates logs, deployment failures, and monitoring issues. Use it to trace an incident and work out a fix.

- subagent · `type=agent` · Claude Code · 2328 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/devops-infrastructure/devops-troubleshooter.md
- Updated: 2026-10-25
- HTML: https://affpapa.org/en/nevibecode/agents/devops-troubleshooter

## What it does

The subagent examines logs, metrics, and traces, tests possible explanations, and helps identify why an incident occurred. It covers container and network debugging, suggests commands to investigate problems, and can help plan a rollback or a temporary fix. Its response can also include monitoring queries and follow-up actions.

It has access to `Read`, `Write`, `Edit`, `Bash`, and `Grep`, so it can inspect and edit files, search a project, and run commands. ELK, Datadog, and `kubectl` appear among its focus areas. This is an incident-response subagent, not a monitoring service; monitoring setup is part of the troubleshooting work it can suggest.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --agent devops-infrastructure/devops-troubleshooter
```

2. **Manually: put the files in place**
- File: `.claude/agents/devops-troubleshooter.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/devops-troubleshooter.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/devops-troubleshooter.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/devops-infrastructure/devops-troubleshooter.md

## When to use it
- trace an incident using logs and metrics
- investigate a container issue with `kubectl`
- plan a rollback after a failed deployment
- draft monitoring queries for an incident
- write follow-up actions after an outage

## Example prompts
- Investigate this incident using its logs and metrics, test possible causes, and report the likely root cause.
- Help debug this container issue: suggest `kubectl` commands and checks.
- Plan a deployment rollback and outline ways to detect a repeat of the issue.

## Similar
- [devops-incident-responder](https://affpapa.org/en/nevibecode/agents/devops-incident-responder.md) — subagent · 206 installs
- [devops-oncall](https://affpapa.org/en/nevibecode/plugins/devops-oncall.md) — plugin · ★ 40418
- [DevOps Expert](https://affpapa.org/en/nevibecode/agents/devops-expert.md) — subagent · ★ 40418
- [security-auditor](https://affpapa.org/en/nevibecode/agents/voltagent-community-security-auditor.md) — subagent · 10718 installs
- [error-detective](https://affpapa.org/en/nevibecode/agents/error-detective.md) — subagent · 7557 installs
- [devops-engineer](https://affpapa.org/en/nevibecode/agents/devops-engineer.md) — subagent · 7392 installs
- [deployment-engineer](https://affpapa.org/en/nevibecode/agents/deployment-engineer.md) — subagent · 6079 installs
- [security-engineer](https://affpapa.org/en/nevibecode/agents/security-engineer.md) — subagent · 3243 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 224 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md