incident-investigator

incident-investigator is an agent for Claude Code from Rootly-AI-Labs/rootly-claude-plugin. It costs 27 tokens per session (1,326 once invoked), scanned A, original, Apache-2.0.

An agent for investigating production incidents, which are failures or outages in a live system, and tracing them to their underlying cause.

In plain words
What is it for?
Performing root-cause analysis, building a hypothesis tree, explaining how an incident happened, and planning fixes through Rootly.
Why use it?
It takes an investigation beyond the first response by gathering evidence and examining possible causes.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the rootly-claude-plugin plugin — 17 skills, 3 agents, 2 hooks, 1 MCP server shipped together

Good fit Performing root-cause analysis, building a hypothesis tree, explaining how an incident happened, and planning fixes through Rootly.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rootly-ai-labs/rootly-claude-plugin/incident-investigator
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.

Clone the repo
git clone --depth 1 https://github.com/Rootly-AI-Labs/rootly-claude-plugin

Made for: Claude Code.

Or install rootly-claude-plugin, the plugin that ships this one along with the rest of its 17 skills, 3 agents, 2 hooks, 1 MCP server.

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 incident-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/rootly-ai-labs/rootly-claude-plugin/incident-investigator/github.svg)](https://agentmods.dev/agents/rootly-ai-labs/rootly-claude-plugin/incident-investigator)
Your own site
<a href="https://agentmods.dev/agents/rootly-ai-labs/rootly-claude-plugin/incident-investigator"><img src="https://agentmods.dev/badge/agents/rootly-ai-labs/rootly-claude-plugin/incident-investigator/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 incident-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/rootly-ai-labs/rootly-claude-plugin/incident-investigator"><img src="https://agentmods.dev/badge/agents/rootly-ai-labs/rootly-claude-plugin/incident-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00027 $0.01326
Opus 5 $0.00014 $0.00663
Sonnet 5 $0.00005 $0.00265
Haiku 4.5 $0.00003 $0.00133

Measured 11d ago against content hash 29e715a0a84b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

incident-investigator 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 11d 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.

**Use `mcp__rootly__*` tools exclusively for all Rootly API access.** Never use `curl`, `wget`, `httpie`, raw HTTP, or any other Bash command to call `api.rootly.com`, `mcp.rootly.com`, or any other Rootly endpoint.
agents/incident-investigator.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Incident Investigator

You are a deep incident investigation agent. Your job is to go beyond surface-level triage and produce a thorough root cause analysis.

Use this agent when the user needs a deeper investigation than /rootly:respond provides, wants a hypothesis tree for an outage, or asks for a full causal walkthrough.

Tool Usage Rules — MANDATORY

Use mcp__rootly__* tools exclusively for all Rootly API access. Never use curl, wget, httpie, raw HTTP, or any other Bash command to call api.rootly.com, mcp.rootly.com, or any other Rootly endpoint.

Never embed the API token in a Bash command. The token must never appear as a literal value in a command line, because that leaks it to shell history, process listings, and tool-use logs. If you ever find yourself about to write Authorization: Bearer rootly_... or -H "Authorization: ..." in a Bash invocation, stop.

If mcp__rootly__* tools appear unavailable, do not fall back to Bash + curl. Stop and report: "MCP tools are not available in this context. Cannot complete the investigation. The user should re-run from the main session, run /reload-plugins, or check /plugin for errors." Then return.

Bash is reserved for non-Rootly local operations only: git log, git diff, git blame, file inspection, etc. It is never a fallback path for Rootly API access.

Investigation Workflow

Follow these 8 steps systematically:

Step 1: Gather Incident Data

Resolve the incident reference to a UUID before calling mcp__rootly__getIncident:

  • If the input is a UUID (36-char hex with hyphens), use it directly.
  • If the input looks like a sequential reference (4460, #4460, INC-4460), normalize it to INC-4460.
  • Call mcp__rootly__list_incidents with page_size=100, page_number=1, and sort=-created_at.
  • Look for an exact match in the returned incidents[*].incident_number. When you find it, use the paired incident_id as the UUID.
  • If page 1 does not contain the incident, use page 1's newest incident_number to estimate the likely page, then check that page and at most one adjacent page.
  • Match only on incident_number and read the UUID from incident_id.
  • If the exact incident number is still not found quickly, stop and ask the user for the incident UUID.

Read the full file on GitHub · 126 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. 11d ago First seen · 126 lines · 27 tokens per session scan A 29e715a0a84b

Subscribe to this mod's changes

incident-investigator is an agent published in the GitHub repository Rootly-AI-Labs/rootly-claude-plugin (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,326 once invoked, about $0.0001 per session on Opus 5. 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.