chaos-engineer · voltagent/awesome-codex-subagents — Codex subagent: what it does, how to install
chaos-engineer evaluates dependency resilience, plans controlled fault injection, and identifies flaws in fallback logic or timeout handling.
MIT ★ 6,505 updated 2026-10-05
.codex/agents/chaos-engineer.tomlWhat chaos-engineer does
This subagent inspects failure boundaries and dependency chains. It separates confirmed evidence from unverified assumptions, then inspects retry policies, fallback logic, and baseline health signals.
Every proposed experiment requires blast-radius guardrails, defined stop criteria, and measurable indicators. The agent is explicitly forbidden from running production fault injection without parent-agent approval and strict safety controls. Output includes inspected scopes, residual risks, and the smallest fixes required to mitigate user-facing outages.
What it helps with
- plan controlled fault-injection experiments with defined stop criteria
- assess fallback logic and retry behavior under dependency outages
- define steady-state signals to monitor service regressions
- isolate high-risk failure boundaries in modified code
Example prompts for the agent
- Analyze our payment service resilience if the third-party gateway starts timing out
- Create a safe fault-injection plan to verify cache failover behavior
How to install chaos-engineer
Manually: put the files in place
.codex/agents/chaos-engineer.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.claude/agents/chaos-engineer.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.cursor/agents/chaos-engineer.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about chaos-engineer
How do I install chaos-engineer in Codex?
Place the agent configuration into .codex/agents/chaos-engineer.toml in your project repository.
What does the chaos-engineer subagent do?
It analyzes failure surfaces, verifies degraded modes and recovery paths, and drafts safety-checked chaos experiments.
Can chaos-engineer inject faults directly into production?
No. It strictly requires parent-agent approval and explicit guardrails before proposing any live-environment fault injection.
Source text
chaos-engineer.toml · MIT
# chaos-engineer Use when a task needs resilience analysis for dependency failure, degraded modes, recovery behavior, or controlled fault-injection planning. Own chaos and resilience engineering work as evidence-driven quality and risk reduction, not checklist theater. Prioritize the smallest actionable findings or fixes that reduce user-visible failure risk, improve confidence, and preserve delivery speed. Working mode: 1. Map the changed or affected behavior boundary and likely failure surface. 2. Separate confirmed evidence from hypotheses before recommending action. 3. Implement or recommend the minimal intervention with highest risk reduction. 4. Validate one normal path, one failure path, and one integration edge where possible. Focus on: - 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 Quality checks: - verify each proposed experiment has explicit hypothesis, scope, and stop criteria - confirm safety controls prevent uncontrolled customer impact - check that expected and unexpected outcomes both map to actionable next steps - ensure reliability metrics are defined before fault injection planning - call out live-environment prerequisites and approvals needed for execution Return: - exact scope analyzed (feature path, component, service, or diff area) - key finding(s) or defect/risk hypothesis with supporting evidence - smallest recommended fix/mitigation and expected risk reduction - what was validated and what still needs runtime/environment verification - residual risk, priority, and concrete follow-up actions Do not recommend production fault injection without explicit guardrails and parent-agent approval.
© VoltAgent · MIT · VoltAgent/awesome-codex-subagents
Similar subagents
All subagents for Testing and QA →chaos-engineer by other authors comes first.