A post-incident retrospective generator for Rootly incidents. A retrospective is a written review of what happened, how the response went, and what should improve afterward.

Use it after an incident to produce structured Markdown that can be copied into documentation or a follow-up report.

It collects incident context and related alerts so you do not have to assemble the review manually. It warns before continuing if the incident is still active.

retro — Skill for Claude Code by Rootly-AI-Labs

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.

Any agent

npx skills add Rootly-AI-Labs/rootly-claude-plugin --skill retro

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rootly-ai-labs/rootly-claude-plugin/retro.svg)](https://agentmods.dev/skills/rootly-ai-labs/rootly-claude-plugin/retro)

Your own site

<a href="https://agentmods.dev/skills/rootly-ai-labs/rootly-claude-plugin/retro"><img src="https://agentmods.dev/badge/skills/rootly-ai-labs/rootly-claude-plugin/retro.svg" alt="Measured on agentmods" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 672 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.

Model	Per session	Once invoked
Fable 5.1	$0.00032	$0.00672
Opus 5	$0.00016	$0.00336
Sonnet 5	$0.00006	$0.00134
Haiku 4.5	$0.00003	$0.00067

Measured 8d ago against content hash fcd729a4c54a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

retro 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 8d 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.

skills/retro/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retrospective Generator (experimental)

Experimental: this skill uses context: fork to delegate to the retro-analyst agent. In some Claude Code contexts the forked subagent does not inherit the plugin's MCP tools. If the agent reports MCP tools unavailable, use /rootly:brief <incident> for a basic incident summary instead.

You are generating a structured post-incident retrospective. The output should be copy-pasteable markdown.

Workflow

1. Get Incident Data

The incident ID should be provided in $ARGUMENTS. If not provided, ask the user for it.

Call mcp__rootly__getIncident for the full incident record
Check the incident status:
- If status is started (still active), warn the user: "This incident is still active. Retrospectives are typically done after resolution. Continue anyway?" Wait for confirmation before proceeding.

2. Gather Context

Call mcp__rootly__get_alert_by_short_id or alert search tools for the alert timeline
Call mcp__rootly__find_related_incidents to check for recurring patterns

3. Generate Retrospective

Output as clean, copy-pasteable markdown:

# Retrospective: [Incident Title]

**Incident ID**: [id]
**Date**: [date]
**Duration**: [start] to [end] ([total duration])
**Severity**: [severity]

## Summary
[1-2 sentence summary of what happened]

## Impact
- **Duration**: [time from detection to resolution]
- **Affected services**: [list]
- **Severity**: [level]
- **User impact**: [description if available]

## Timeline
| Time | Event |
|------|-------|
| [time] | [event] |
| ... | ... |

## Root Cause Analysis
[Analysis based on incident data, alerts, and resolution steps]

## Contributing Factors
- [Factor 1]
- [Factor 2]

## What Went Well
- [Positive aspect 1]
- [Positive aspect 2]

## What Could Be Improved
- [Improvement area 1]
- [Improvement area 2]

## Action Items
| Action | Owner | Priority |
|--------|-------|----------|
| [action] | [owner if identifiable] | [high/medium/low] |

## Pattern Note
[If find_related_incidents shows similar past incidents:]
"This is the Nth incident of this type in the last 90 days. Consider systemic fixes."
[If no similar incidents: omit this section]

Read the full file on GitHub · 87 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.

8d ago First seen · 87 lines · 32 tokens per session scan A fcd729a4c54a

Subscribe to this mod's changes

retro is a skill published in the GitHub repository Rootly-AI-Labs/rootly-claude-plugin (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 672 once invoked, about $0.0002 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.

Debugging

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens