Which AI agents does this loop work with?

Keep docent updated on idle 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.

/loop automationlow riskbeginnersafety D · 40 · open-endedpre-dates current gate · under review

Keep docent updated on idle

Re-run docent updates on each idle tick until you cancel the loop.

prompt

→ Claude

/loop /docent update — re-runs on each idle tick until cancelled

claude-code

Implementation note

When to use: keeping a docent/assistant context file in sync automatically whenever your session goes idle, instead of remembering to trigger it manually. Safety: confirm the docent-update step is idempotent (safe to re-run back-to-back) since idle ticks can fire repeatedly with no natural cap — set an iteration or time budget if the idle interval is short.

Source: calumjs ↗

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 ↗