Which AI agents does this loop work with?

Codex App Automations (Scheduled Agent Runs) is written for claude-code.

Is this loop safe to run unattended?

This loop is graded D (40/100) by looprepo's automatic safety evaluator, which checks for exit conditions, iteration budgets, verification steps, and scoping before publishing.

/ralph automationmedium riskintermediatesafety D · 40 · open-ended ★ OpenAI

Codex App Automations (Scheduled Agent Runs)

Codex's native answer to scheduled agent loops: define a prompt plus a schedule in the Codex app and it runs in the cloud on cadence — nightly dependency audits, morning issue triage — with no terminal open. The Codex-side equivalent of Claude Code Routines.

prompt

→ Claude

Define an Automation in the Codex app: a prompt + schedule that runs in the cloud on cadence (e.g., nightly dependency audit, morning triage of new issues), no terminal open.

claude-code

Implementation note

When to use: recurring agent work on the Codex side of the fence — nightly dependency audits, morning triage of new issues — where you want cloud execution on a schedule with no terminal open. It is the Codex-side equivalent of Claude Code Routines. How it works: define an Automation in the Codex app: a prompt plus a schedule. The automation then runs in the cloud on that cadence — your machine can be off entirely. Note this is a Codex-app pattern, not a Claude slash command; it is filed in this directory as a harness pattern. Safety: cloud-scheduled agents run unattended by definition, so the discipline lives in the prompt: give automations report-shaped work (audit, triage, summarize) before mutation-shaped work, and make any write action land as a reviewable artifact — a PR or an issue — rather than a direct change. Review the first few scheduled outputs before extending its scope.

Source: OpenAI (Codex app docs) ↗

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

source ↗