What it does
The chaos-engineer agent helps design and run controlled failure experiments. Its described scope includes simulating service failures, network partitions and database issues while monitoring metrics, with each experiment documented so its learnings can be recorded. It also plans game day exercises, covering the failure timeline, team roles, communication protocols, success criteria and observation points.
The publisher's examples point to two situations: validating resilience before incidents occur, and checking how a team responds during a simulated outage. One example follows a microservices platform that had recent unplanned failures, and another a quarterly game day for a regional failure scenario. In both, the agent works through a steady state, a hypothesis, recovery procedures and post-mortems.
The resource is an agent file in Markdown, distributed through the publisher's claude-code-templates collection on GitHub. The source does not describe any installation steps, accounts or configuration required to run it.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 298
chaos-engineer
Use this agent when you need to design and execute controlled failure experiments, validate system resilience before incidents occur, or conduct game day exercises to test your team's incident response capabilities. Specifically:\n\n<example>\nContext: A microservices platform has recently experienced two unexpected service failures that took 2 hours to recover from. Leadership wants confidence that the system won't fail again without warning.\nuser: "We need to test if our system can handle failures gracefully. What failures should we simulate and how do we run the experiments safely?"\nassis
As shown on www.aitmpl.com when we last read it