OperationsPROPRO REQUIREDFC-OPS-016
Chaos Claw
chaos-claw
v0.2.0May 25, 2026Chaos engineering — blast radius limits, rollback steps, and reproducible experiments that reveal weaknesses before incidents do
The best time to break your system is when you're watching—with runbooks open and on-call engineers at their desks, not in bed. I design chaos experiments with bounded blast radii, measurable steady-state hypotheses, and rollback triggers you can pull before the experiment becomes the incident. GameDays aren't theater; they're the only honest way to test your assumptions about resilience.
OpenClaw
Hermes
Claude Code
Codex
Cursor
Windsurf
Aider
OllamaPRIMARY ACTION
Unlock with ProCOMPATIBLE WITH
OpenClawHermesClaude CodeCodex+4
8 compatible tools5 output formats
When to Use
- Harden deployment and release workflows
- Improve observability and alert readiness
- Define environment standards
- Prepare operational runbooks
Compatible Frameworks
OpenClawHermesClaude CodeCodexCursorWindsurfAiderOllama8 TOOLS
Quality Gates
- no fake claims
- blast radius limited
- rollback steps defined
- experiment reproducible
5 GATES DEFINED
Expected Outputs
Chaos Experiment Design DocumentGameDay Runbook with TimelineFault Injection Playbook by Failure ModeResilience Gap Report with Prioritized Remediation CardsExperiment Results Dashboard Snapshot
Native exports per tool
OpenClaw10 files
openclaw/AGENTS.mdopenclaw/SOUL.mdopenclaw/TOOLS.md+7 moreHermes5 files
hermes/skills/flickclaw/chaos-claw/SKILL.mdhermes/skills/flickclaw/chaos-claw/references/workflow.mdhermes/skills/flickclaw/chaos-claw/references/quality-gates.md+2 moreClaude Code6 files
claude-code/CLAUDE.mdclaude-code/.claude/skills/chaos-claw/SKILL.mdclaude-code/.claude/skills/chaos-claw/references/workflow.md+3 moreCodex5 files
codex/AGENTS.mdcodex/.flickclaw/agents/chaos-claw/codex.mdcodex/.flickclaw/agents/chaos-claw/workflow.md+2 moreCursor3 files
cursor/.cursor/rules/flickclaw-chaos-claw.mdccursor/.cursor/rules/flickclaw-chaos-claw-workflow.mdccursor/.cursor/rules/flickclaw-chaos-claw-quality-gates.mdcWindsurf3 files
windsurf/.windsurf/rules/flickclaw-chaos-claw.mdwindsurf/.windsurf/rules/flickclaw-chaos-claw-workflow.mdwindsurf/.windsurf/rules/flickclaw-chaos-claw-quality-gates.mdAider3 files
aider/CONVENTIONS.mdaider/aider.mdaider/.aider.conf.ymlOllama4 files
ollama/Modelfileollama/system-prompt.mdollama/template.md+1 moreInstall Commands
Install the FlickClaw CLI, then select your AI agent framework below to get the correct install command.
Step 1: Install CLI (one-time)
npm install -g @flickclaw/cli@latestStep 2: Select Framework
OpenClaw
npm exec --yes @flickclaw/cli@latest -- install chaos-claw --target openclawDownload as ZIP
Example Prompt
Try this prompt with Chaos Claw to see what it can do:
Review the deployment pipeline and monitoring. Identify bottlenecks and single points of failure. Produce Chaos Experiment Design Document, GameDay Runbook with Timeline, Fault Injection Playbook by Failure Mode.Example Output
IllustrativeWhat a typical Chaos Claw report looks like:
# Chaos Claw — Assessment Report **Project**: microservices-cluster **Context**: a Kubernetes cluster running 12 microservices with Istio and Prometheus **Generated**: 2026-07-10 ## Executive Summary The Chaos Claw completed its review of microservices-cluster (a Kubernetes cluster running 12 microservices with Istio and Prometheus). 3 findings were identified with concrete remediation steps. All quality gates were verified before delivery. ## Findings | # | Severity | Area | Finding | Recommended Action | |---|----------|------|---------|-------------------| | 1 | **P0** | Deployment | No rollback strategy defined for 4 services | Add Helm rollback hooks and deployment pause windows | | 2 | **P1** | Monitoring | Alert fatigue from 200+ low-priority alerts/day | Consolidate alerts, add severity routing, mute during maintenance | | 3 | **P2** | Cost | 3 dev clusters running 24/7 without downscaling | Add cron-based scaling to zero during off-hours | ## Quality Gates - [✓] Blast radius bounded and documented per experiment - [✓] Rollback mechanism verified before fault injection - [✓] Steady-state hypothesis defined with measurable criteria ## Outputs Generated - **Chaos Experiment Design Document**: Included in the report above. - **GameDay Runbook with Timeline**: Included in the report above. - **Fault Injection Playbook by Failure Mode**: Included in the report above. - **Resilience Gap Report with Prioritized Remediation Cards**: Included in the report above. - **Experiment Results Dashboard Snapshot**: Included in the report above. ## Validation - [x] All quality gates passed (3/3) - [x] 3 findings documented with severity and remediation - [x] 5 output sections generated - [x] Evidence collected and referenced --- *This is an illustrative example output from FlickClaw. Results vary based on project context.*
RELATED AGENTS