← Explore all agents

OPERATIONS / Agency Agents community

Production incident coordination planner

A response-coordination profile with role, timeline, mitigation and follow-up templates.

“Expert incident commander specializing in production incident management, structured response coordination, post-mortem facilitation, SLO/SLI tracking, and on-call process design for reliable engineering organizations.”

01 / THE REASONING

Why this made the selection.

  • It separates commander, technical lead, communications and scribe responsibilities so troubleshooting and external updates have clear owners.
  • Recovery is assessed against observed service indicators before an all-clear, and postmortem actions need owners and deadlines.

02 / THE REVIEW RECORD

What we actually inspected.

Source review has boundaries.
A clear record is more useful than a “safe” badge.

Material inspected

  • engineering/engineering-incident-response-commander.md (pinned complete source retained)
  • LICENSE
  • Repository README and current official host configuration documentation

Our findings

  • It separates commander, technical lead, communications and scribe responsibilities so troubleshooting and external updates have clear owners.
  • Recovery is assessed against observed service indicators before an all-clear, and postmortem actions need owners and deadlines.

Not established by this review

  • Source review only: no agent was installed or invoked. Task correctness, effective host restrictions and integration behaviour were not tested.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

Use the role in your project.

Upstream setup instructions ↗
  1. Read the pinned source and its licence, then configure an explicitly bounded host context.
  2. Check the original display-style name and optional color/emoji/vibe metadata against the installed host requirements before loading a working copy. Current Claude Code documentation says unknown frontmatter fields are ignored; it does not establish a need to rewrite these names. Keep the archived/downloaded original unchanged.
  3. Load real runbooks and metrics, reconcile the escalation matrix and restrict production/messaging tools to the authorized incident scope.
  4. Supply incident symptoms, timestamps, actual impact, ownership and established escalation policy.

Before you start

  • Current incident evidence and service ownership
  • Existing runbooks, escalation and communication policy

04 / FOLLOW THE EVIDENCE

The source trail.

Our notes are separate from the original resource.
Check upstream before adopting a new version.

  1. https://github.com/msitarzewski/agency-agents/blob/bd956db032d907387e6b9ddebff3e18f1de8c679/engineering/engineering-incident-response-commander.md

    Supports: Workflow, inputs, outputs and stated boundaries

  2. Applicable licence ↗Checked

    https://github.com/msitarzewski/agency-agents/blob/bd956db032d907387e6b9ddebff3e18f1de8c679/LICENSE

    Supports: Redistribution and attribution

  3. https://code.claude.com/docs/en/sub-agents.md

    Supports: Host loading and effective permission boundaries

  4. https://sre.google/workbook/alerting-on-slos/

    Supports: Dependency setup and source-review boundary

Evidence & Ask