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.

prompt
→ Claude
Automation toolkit running repeated `claude` sessions with per-iteration cost and token monitoring; inspired by Dex Horthy's context-engineering talk.
claude-code

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.

Source: li0nel/claude-loop

More automation loops

Run workflows with dynamic sub-agents

/goalnew

Split a task into packets, run sub-agents in parallel, synthesize results, and verify completion.

prompt
→ Claude
/goal loop and verify until complete
automationlow risk

Run agent turns until goal met

/goalnew

Agent executes repeated turns toward a condition, with a lightweight evaluator checking progress after each turn until the goal is reached.

prompt
→ Claude
/goal <condition turns a prompt into a durable objective. Thanos immediately starts a turn toward the condition, and after each turn a fresh, tool-less side-channel evaluator (a one-shot completeSimple call, not a subagent — so no extra agent turn and no re-entrancy) reads the last turn's evidence and returns MET / NOT MET . NOT MET auto-continues another turn with the reason as guidance; MET clears the goal and records the achievement. Unparseable evaluator output is treated as NOT MET (fail-safe: it never declares a false "done
automationmedium risk

Run agent until goal met

/goalnew

Queue agent turns with goal context until your objective is achieved, treating the goal as untrusted data.

prompt
→ Claude
/goal <objective , after /goal resume , and after every agent turn that leaves the goal active , the extension queues Codex's goal continuation prompt as hidden model-visible context. The objective is XML-escaped and wrapped as untrusted user data so it does not become higher-priority instructions
automationlow risk