incident-postmortem

A workflow for investigating a software incident and creating a blameless postmortem—a record of what happened, why, and how to prevent it.

In plain words
What is it for?
Use it to build incident timelines, analyze root causes and recurring patterns, create prevention tickets in Jira, and publish findings to Confluence.
Why use it?
It gathers evidence from incident tickets, chat, code changes, and documentation so the team can learn from failures without focusing on blame.

Command for Claude Code

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.

agentmods
npx agentmods add commands/parkerm2/create-claude-workflow/incident-postmortem
Clone the repo
git clone --depth 1 https://github.com/ParkerM2/create-claude-workflow

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,178 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00019 $0.06178
Opus 5 $0.00010 $0.03089
Sonnet 5 $0.00004 $0.01236
Haiku 4.5 $0.00002 $0.00618

Measured 2d ago against content hash 0c001306a8b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

incident-postmortem 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 2d 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.

.claude/commands/incident-postmortem.md · 714 lines

How it starts

The opening of the file, as written. The whole thing — 714 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Incident Postmortem Workflow

Complete incident-to-prevention pipeline: generate comprehensive blameless postmortems, create Jira tickets for prevention, detect incident patterns, and publish findings to Confluence with Slack notifications.

Integration Points

  • Jira MCP: Fetch incident tickets, auto-create prevention tickets, link postmortem
  • Slack MCP: Extract incident channel messages, post postmortem summary
  • Confluence MCP: Publish postmortem documents, create searchable knowledge base
  • GitHub MCP: Query commits/PRs during incident window for timeline
  • Memory: Incident history, pattern detection, prevention ticket tracking
  • Engineering Plugin: Integration with /incident-response command output

Workflow Phases

Phase 1: Incident Intake & Data Gathering

Collect incident details from multiple sources:

  1. Incident Context Resolution

    • Accept inputs (in priority order):
      • Jira incident ticket: SEV1-2024-001
      • Slack channel: #incident-2026-03-27
      • Direct description: "Database connection pool exhausted"
    • Auto-detect: Check memory for recent incidents (< 24 hours old)
  2. Interactive Incident Details (if not provided)

    • Prompt user with structured form:
      Incident Title: _______________________________
      Severity (SEV1/2/3/4): _______
      Start Time (UTC): _______________________________
      End Time / Resolution Time (UTC): ______________
      Root Cause (brief): _____________________________
      Systems Affected: ______________________________
      Estimated User Impact: __________________________
      Lead Investigator: ______________________________
      
  3. Fetch from Jira Incident Ticket

    • If --ticket SEV1-2024-001 provided:
      • Call jira_get_issue(SEV1-2024-001)
      • Extract: Summary, description, status, timestamps
      • Get comments (investigation notes from team)
      • Identify: Reporter, assignee, watchers (participants)
  4. Fetch from Slack

    • If --slack-channel #incident-2026-03-27 provided:
    • Extract messages from incident window:
      • Initial report message and timestamp
      • Key investigation messages
      • Resolution confirmation
      • Message-based timeline of discovery
    • Identify participants: Extract @mentions and reactions

Read the full file on GitHub · 714 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. 2d ago First seen · 714 lines · 19 tokens per session scan A 0c001306a8b4

Subscribe to this mod's changes

incident-postmortem is a command published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 6,178 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 2026-08-31.