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
Ship production-grade apps autonomously
Hand an idea to Claude Code; it authors specs, designs, builds, tests, secures, and ships until enterprise done or budget exhausted.
claude-progress.txt harness pattern (Anthropic)
Anthropic's first-party file-as-memory harness for long-running agents: every fresh-context session recovers state from a progress file and the git log, does one unit of work, updates the file, commits, and exits.
Complete all tasks in tasks.md
Work through your tasks.md file, completing each task until none remain or max iterations is reached.