awesome-loops

Automation loops for Claude, Cursor, and Codex

Open them in Claude, add them to Cursor, or launch them with Codex. Every submission is a Markdown automation reviewed through GitHub.

Claude Cursor Codex
Engineering

Adversarial review loop

Use a fresh context to review a diff against the original requirements, then fix only correctness gaps.

code-review verification pull-request
Operations

Chief of staff inbox triage

Recurring inbox and Slack scan that identifies unanswered work, researches context, and drafts replies without sending.

inbox slack gmail
Engineering

Explore, plan, code, PR loop

Separate codebase exploration from implementation, then verify the change and open a reviewable PR.

planning pull-request tests
Engineering

Fan-out migration loop

Generate a file list, test the migration prompt on a small sample, then run the same constrained task across many files.

migration parallel batching
Operations

Feedback to render loop

Monitor a feedback thread, revise the artifact when comments arrive, re-render, and post the new version for review.

feedback rendering slack
Evaluation

Full product evaluation loop

Define realistic scenarios for every major capability, fix failures, and rerun the whole evaluation set.

evaluation qa release
Engineering

Goal with test-suite oracle

Give a long-running agent migration a hard finish line by requiring it to satisfy an existing test suite.

migration goals tests
Operations

Memory diff workstream loop

Keep a long-running workstream grounded by writing decisions and open loops to disk, then reviewing the diff.

memory workstreams notes
Documentation

Nightly changelog loop

Review the day's changes and update the changelog with user-visible updates or a recorded no-change result.

changelog documentation release-notes
Documentation

Overnight docs sweep

Review recent code changes, update stale documentation, and open a focused PR before the next workday.

documentation pull-request maintenance
Release

Post-release baseline loop

After a release lands, rerun standard benchmarks and store the new baseline with environment details.

benchmarks release performance
Data quality

Production data cleanup loop

Audit records against an allowed definition, clean invalid data, improve classification, and prove the retained data is valid.

data-quality production cleanup
Operations

Production error sweep

Scan production logs, fix actionable root causes, verify the fix, and send a concise status update.

production logs incident
Evaluation

Quality streak loop

Run realistic cases until N pass in a row, restarting the streak whenever a failure is found and fixed.

evaluation qa regression
Engineering

Repository cleanup loop

Inspect branches, worktrees, commits, and PRs; recover valuable work and remove stale state with evidence.

git cleanup maintenance
Growth

SEO and GEO visibility loop

Audit indexability, answer readiness, structured data, and query coverage, then fix the highest-impact gap and rerun the benchmark.

seo geo growth
Release

Stale-safe batch release loop

Review pending changes, exclude stale or unfinished work, combine only valid changes, and release from current main.

release pull-request ci
Customer support

Support refund polling loop

Poll a customer-support chat until an agent joins, then respond quickly with the goal and evidence.

support polling browser
Engineering

Test-suite speed loop

Make a test suite faster without losing coverage or behavior, proving each improvement with repeatable timing.

tests performance ci
Evaluation

Visual verification loop

Compare the implemented UI against a screenshot or design, list differences, fix them, and repeat.

ui screenshots qa

Create automation loop

Submit opens a GitHub issue. A repository workflow turns the issue into a PR.