Reusable prompts and step-by-step workflows that let coding agents self-pace through a task until it's done.
Review your own diff like a senior reviewer, fix issues, and repeat for three passes before opening the PR.
Weekly loop to check outdated dependencies, propose safe upgrades, and open a summary.
Upgrade a single outdated package per iteration, fix breakages, and commit — safer than bulk npm update.
Rebase or merge target branch, resolve conflicts file by file, and loop until the branch is current and tests pass.
Run your test suite, fix the smallest root cause on failure, and repeat until every test passes.
Write a small throwaway script to reproduce a bug, run it, read output, and iterate until the root cause is proven.
Implement from a written spec.md checklist — each iteration completes one unchecked requirement with verification.
Ship features without bloating the client bundle — loop until size checks pass under your budget threshold.
Run Playwright or Percy visual snapshots on UI changes; fix unintended diffs until baselines match intentionally.
Run end-to-end tests, fix UI and integration failures, and loop until the E2E suite passes.
Common questions about reusable Loops for AI coding agents
A loop is a reusable workflow for AI coding agents built around four parts: a goal, a check command that objectively verifies progress, an exit condition, and a max-iteration limit. Paste the kickoff prompt into your agent and it self-paces through the task, re-running the check command after each pass until the exit condition is met.
A normal prompt is one instruction for one turn. A loop is the system around repeated turns — it tells the agent how to verify its own work and when to stop, so it can keep going without you re-prompting it after every attempt. This practice is known as loop engineering.
Most loops on this page are agent-agnostic — the kickoff prompt is plain text you can paste into Claude Code, Cursor, Codex, or any other coding agent. Each loop's page lists which agents it was specifically built and tested for.
Use a loop when a task needs several revision passes and has an objective acceptance check, such as fixing tests, resolving CI failures, reviewing code, verifying a deployment, or completing a large refactor. One-off questions and tasks without a clear definition of done usually do not need a loop.
Choose a stable, repeatable check with a meaningful exit code, such as tests, type checking, linting, or a deployment health check. Define an observable completion state and set a maximum iteration count so the AI agent cannot retry forever.
A loop repeatedly executes prompts and commands, so restrict file, network, secret, and deployment access; run risky work in an isolated branch or sandbox; and keep iteration limits and human review. Never let an unreviewed loop run destructive commands.
