/scheduleautomationmedium riskintermediatesafety D · 40 · open-endedSabrina Ramonovpre-dates current gate · under review

/goal + Routines overnight combo

The two-layer answer to how do I run this overnight: /goal drives in-session work to done, while a scheduled Routine keeps recurring unattended work running on Anthropic's cloud with your laptop closed.

prompt
→ Claude
/schedule a Routine (runs on Anthropic cloud, laptop closed) for recurring unattended work, and use `/goal` for in-session iterate-to-done — the two-layer overnight pattern.
claude-code

Implementation note

When to use: the how-do-I-run-this-overnight question — you want in-session work driven to completion while you watch, and recurring unattended work running with the laptop closed. This is the two-layer answer. How it works: /goal handles the in-session layer, iterating a task to its done condition while you are at the keyboard. /schedule creates a Routine for the recurring layer, which runs on Anthropic's cloud on cadence — no local machine required, laptop closed. The split is deliberate: goals are for converging on a defined outcome now, Routines are for standing work that should happen without you. Safety: the two layers carry different risk profiles. Goals run under your observation with your local permissions; Routines run unattended in the cloud, so scope what a Routine can touch conservatively and give it report-heavy, mutation-light work until you trust its judgment. Put turn caps in your goal text as usual.

Source: Sabrina Ramonov

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