domains / families / agent-tooling / checkpointed-agent-loop

checkpointed-agent-loop

separate

Run long or failure-prone Claude Code tasks as bounded, resumable loops with a durable state machine, attempt budget, and verification evidence checkpoint.

When to use

• A migration, refactor, test repair, or investigation may span multiple sessions.
• A bounded retry loop is safer than repeatedly improvising from conversation history.
• A task needs a durable next action and a record of which verification actually ran.
• You need to stop at an external dependency or a human decision without claiming success.

When not to use

• one-line edits
• workflows with their own durable runner

Skill page

Source