Custom loop.md — Project-Level Default for Bare /loop
A team-config pattern: a loop.md file in the project root overrides the built-in maintenance prompt, so any teammate running bare /loop gets your project's canonical loop — run lint, typecheck, and tests, fix anything red, stop when clean.
Implementation note
When to use: your team runs bare /loop often enough that the built-in default maintenance prompt is a missed opportunity — you want every teammate's reflexive /loop to run your project's canonical checklist instead. How it works: place a loop.md file in the project root; it replaces the built-in maintenance prompt whenever someone runs bare /loop. A typical loop.md: run lint, typecheck, and tests; fix anything red; update the CHANGELOG; stop when clean. Because the file is versioned with the repo, the team's default loop evolves through normal code review. Safety: this is configuration, not a runnable loop itself — the safety of bare /loop becomes whatever your loop.md says, so write an explicit stop condition (stop when clean) and keep the scope conservative, since people will invoke it casually. Note the documented limit: loop.md maxes out at 25KB per Anthropic's docs. Review changes to it like code, because it is code.
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.