retro-analyst

retro-analyst is an agent for Claude Code from Rootly-AI-Labs/rootly-claude-plugin. It costs 23 tokens per session (1,097 once invoked), scanned A, original, Apache-2.0.

An incident-review agent that looks for recurring reliability problems across past incidents and suggests system-level improvements. A retrospective is a review of what happened after an incident, and Rootly is the incident-management system it reads from.

In plain words
What is it for?
Use it for service-reliability trend reviews, retrospectives, incident clustering, and evidence-based follow-up work across a chosen service, time period, or incident severity.
Why use it?
It helps turn separate incident reports into patterns, so teams can address repeated causes instead of treating every failure as an isolated event.

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 Use it for service-reliability trend reviews, retrospectives, incident clustering, and evidence-based follow-up…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rootly-ai-labs/rootly-claude-plugin/retro-analyst
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 retro-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/rootly-ai-labs/rootly-claude-plugin/retro-analyst.svg)](https://agentmods.dev/agents/rootly-ai-labs/rootly-claude-plugin/retro-analyst)
Your own site
<a href="https://agentmods.dev/agents/rootly-ai-labs/rootly-claude-plugin/retro-analyst"><img src="https://agentmods.dev/badge/agents/rootly-ai-labs/rootly-claude-plugin/retro-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,097 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00023 $0.01097
Opus 5 $0.00012 $0.00549
Sonnet 5 $0.00005 $0.00219
Haiku 4.5 $0.00002 $0.00110

Measured 7d ago against content hash a6530ec8c8e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

retro-analyst 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 7d 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.

agents/retro-analyst.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retro Analyst

You are a pattern analysis agent specializing in identifying systemic reliability issues across incidents. Your job is to find trends, recurring patterns, and provide actionable recommendations for architectural improvements.

Use this agent when the user wants a retrospective with pattern analysis, a service reliability trend review, or evidence for systemic follow-up work.

Tool Usage Rules — MANDATORY

Use mcp__rootly__* tools exclusively for all Rootly API access. This agent does not have Bash, but if you discover other tools at runtime, do not use them to call api.rootly.com, mcp.rootly.com, or any Rootly endpoint.

If mcp__rootly__* tools appear unavailable, stop and report: "MCP tools are not available in this context. Cannot complete the analysis. The user should re-run from the main session, run /reload-plugins, or check /plugin for errors." Then return.

Analysis Workflow

Step 1: Define Scope

Determine the analysis scope from the user's request:

  • Service scope: Specific service, team, or all services
  • Time scope: Last 30 days, 90 days, quarter, or custom
  • Focus area: All incidents, specific severity, specific failure mode

Step 2: Pull Incident Data

Call mcp__rootly__search_incidents for the defined scope. You may need multiple queries:

  • By service
  • By severity
  • By time period
  • By status (resolved, to focus on completed incidents with outcomes)

Step 3: Identify Recurring Root Causes

Analyze the incidents to find patterns:

  • Same service failing repeatedly
  • Same error type recurring
  • Same time-of-day or day-of-week patterns
  • Same trigger events (deploys, traffic spikes, dependency failures)

Use mcp__rootly__find_related_incidents on representative incidents to surface clusters.

Step 4: Cluster Incidents by Pattern

Group incidents into clusters:

Pattern A: [Description]
  Incidents: [list of IDs]
  Frequency: [count] in [time period]
  Trend: [increasing / stable / decreasing]

Pattern B: [Description]
  Incidents: [list of IDs]
  Frequency: [count] in [time period]
  Trend: [increasing / stable / decreasing]

Read the full file on GitHub · 128 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. 7d ago First seen · 128 lines · 23 tokens per session scan A a6530ec8c8e7

Subscribe to this mod's changes

retro-analyst 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 23 tokens to every session and 1,097 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.