claude-loop — iterative sessions with cost tracking
An automation harness that runs repeated Claude Code sessions while tracking cost and tokens per iteration — the reference answer to the number-one objection to agent loops: runaway spend.
Implementation note
When to use: you are sold on iterative agent sessions but not on surprise bills — this harness exists specifically to answer the number-one objection to agent loops, runaway spend. Inspired by Dex Horthy's context-engineering talk. How it works: an automation toolkit that runs repeated claude sessions in a loop while recording cost and token usage per iteration, so you can see exactly what each cycle consumed rather than discovering the total afterward. The per-iteration granularity is what makes the data actionable: an iteration whose token count spikes is visible immediately, and trends across a run tell you whether the loop is converging or thrashing. Safety: measurement is the rail here — per-iteration cost visibility is what lets you set informed caps and kill a run that is trending wrong. Pair it with hard limits (iteration caps, budget ceilings), since tracking alone observes spend rather than stopping it.
More automation loops
Run workflows with dynamic sub-agents
Split a task into packets, run sub-agents in parallel, synthesize results, and verify completion.
Run agent turns until goal met
Agent executes repeated turns toward a condition, with a lightweight evaluator checking progress after each turn until the goal is reached.
Run agent until goal met
Queue agent turns with goal context until your objective is achieved, treating the goal as untrusted data.