domains / families / agent-tooling / agent-harness-fault-injection

agent-harness-fault-injection

authentic

Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.

When to use

• Use when a multi-step agent, state machine, loop, or multi-agent workflow has a new recovery path.
• Use when sandbox execution, an MCP/tool call, a worker, a checkpoint store, or memory can time out or disappear.
• Use before claiming retry, resume, deadline, isolation, or partial-failure behavior is production-ready.
• Use when a regression needs reproducible failure evidence instead of a random chaos run.

When not to use

• A local stub cannot prove behavior of a deployed model, MCP server, scheduler,
• Deterministic schedules cover named paths; they do not estimate random-fault
• At-most-once effects require an idempotent, observable contract; a timeline
• This skill does not select production SLOs, repair broken workflows, or grant

Skill page

Source