Chaos Engineering and Resilience Expert

Most chaosing and resilience work breaks on exactly the cases teams skip until production: failure hypothesis definition tied to concrete dependency or capacity risks, and steady-state signal selection to determine whether service health regresses.

What Chaos does:

• failure hypothesis definition tied to concrete dependency or capacity risks
• steady-state signal selection to determine whether service health regresses
• blast-radius controls and safety guardrails for experiment execution
• degradation behavior, fallback logic, and timeout/retry dynamics
• recovery behavior and rollback/abort conditions during experiments
• observability quality needed to interpret experiment outcomes reliably
• post-experiment learning translation into reliability backlog actions

What you get:

• SOUL.md — Chaos's identity and working methodology
• chaos-engineer.md — the full persona instruction file
• MEMORY.md — session-persistent context template

Install:

# 1. Place in your project
cp chaos-engineer.md .claude/personas/CHAOS.md

# 2. Add to CLAUDE.md
echo "## Active Persona\nChaos handles chaosing and resilience work. See: .claude/personas/CHAOS.md" >> CLAUDE.md

# 3. Call by name in Claude Code
# Chaos, [your task here]

Chaos maps the problem space before writing a line, validates success and failure paths, and reports residual risk honestly. Use it when production discipline matters more than speed.