# rootly-incident-responder

A Claude Code subagent for Rootly incident triage, historical matches, on-call coordination, and reviewed remediation plans.

- subagent · `type=agent` · Claude Code · 167 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/development-tools/rootly-incident-responder.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/rootly-incident-responder

## What it does

rootly-incident-responder gathers incident details from Rootly, including severity, affected services, environment, status, and alert order. It searches earlier incidents for related cases and uses their outcomes to suggest possible responses.

The subagent can identify the current on-call team, account for regional coverage, and compare the incident with recent GitHub changes. Its reports include sources, confidence, and reasoning; production rollbacks and other high-impact actions stay behind a human approval step.

A Rootly MCP server is required for the incident workflow. GitHub MCP is optional and supports code-change correlation. Without Rootly MCP, the subagent cannot work with Rootly data.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --agent development-tools/rootly-incident-responder
```

2. **Manually: put the files in place**
- File: `.claude/agents/rootly-incident-responder.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/rootly-incident-responder.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/rootly-incident-responder.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/development-tools/rootly-incident-responder.md

## When to use it
- investigate a production incident
- match an outage with earlier Rootly incidents
- compare a failure with recent GitHub changes
- prepare a handoff for the on-call team
- draft a remediation plan for approval

## Example prompts
- Investigate incident `INC-123` in Rootly, find related incidents, and show confidence for each lead.
- Identify the first alerts in this incident and compare the timeline with recent GitHub changes.
- Draft remediation actions and wait for my approval before any critical production change.

## Similar
- [frontend-developer](https://affpapa.org/en/nevibecode/agents/voltagent-community-frontend-developer.md) — subagent · 40905 installs
- [dx-optimizer](https://affpapa.org/en/nevibecode/agents/dx-optimizer.md) — subagent · 1198 installs
- [mlops-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-mlops-engineer.md) — subagent · 1009 installs
- [postgres-pro](https://affpapa.org/en/nevibecode/agents/postgres-pro.md) — subagent · 897 installs
- [agent-installer](https://affpapa.org/en/nevibecode/agents/agent-installer.md) — subagent · 363 installs
- [embedded-systems](https://affpapa.org/en/nevibecode/agents/embedded-systems.md) — subagent · 279 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 804 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