← Explore all agents

RESILIENCE TESTING / VoltAgent

Controlled failure-experiment designer

Frames failure experiments around a steady-state hypothesis, bounded impact, observable recovery and explicit stop controls.

“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.”

01 / THE REASONING

Why this made the selection.

  • The workflow begins in non-production and expands scope gradually rather than beginning with combined failures.
  • It includes human response and communication observations as well as infrastructure/service failures.
  • The profile designs failure experiments that start outside production, with a limited blast radius and a rollback path.
  • Its checklist requires a stated steady state and a hypothesis before an experiment, and it says customer impact is not acceptable.

02 / THE REVIEW RECORD

What we actually inspected.

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

Material inspected

  • categories/04-quality-security/chaos-engineer.md (complete definition)
  • LICENSE (applicable redistribution terms)
  • Host custom-agent documentation; repository installation guidance where applicable

Our findings

  • The workflow begins in non-production and expands scope gradually rather than beginning with combined failures.
  • It includes human response and communication observations as well as infrastructure/service failures.
  • The checklist requires a steady state, a hypothesis, a controlled blast radius, and no customer impact.
  • Experiment patterns say to begin in non-production, test one variable, and keep a rollback path. Blast-radius controls include a manual kill switch.
  • Declared tools are Read, Write, Edit, Bash, Glob, and Grep.
  • The sample progress JSON hard-codes experiments, failures, and an MTTR figure, and the checklist states a rollback time. None of those figures was measured here, and the file does not run an experiment by being read.

Not established by this review

  • No agent was installed or invoked. Host/model compatibility, task accuracy and runtime behaviour were not tested.
  • The resource was not executed and its tools were not called.

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 definition and MIT licence; review the host permissions before use.
  2. Place the reviewed definition in .claude/agents/, supply the system context directly and constrain file/shell/cloud permissions to the agreed diagnostic or test scope.
  3. Provide system dependencies, SLOs, incident history, recovery procedures and a specifically authorized experiment environment.

Before you start

  • Claude Code with the selected model available
  • The specific infrastructure/toolchain and a bounded non-production validation environment

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/VoltAgent/awesome-claude-code-subagents/blob/408d3c9eee2d0c75c12a3abb5de29e53c2ca6b9e/categories/04-quality-security/chaos-engineer.md

    Supports: Workflow, inputs and outputs, Declared tools and constraints, Selection and limitations

  2. https://github.com/VoltAgent/awesome-claude-code-subagents/blob/408d3c9eee2d0c75c12a3abb5de29e53c2ca6b9e/LICENSE

    Supports: Licence and attribution requirements

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

    Supports: Host setup and permission defaults

Evidence & Ask