Source-reviewed loops for agents that need feedback gates, not vague one-shot prompts.
Submit an agent loop for reviewFind the agent loop that should run next
Stop prompting agents step by step. Search source-reviewed loops that define the goal, required context, commands, feedback gates, failure handling, and stop condition.
34+
copy-ready loops
10
active use cases
5
agent families
Goal before action
Every loop defines what done means before the agent changes files.
Feedback drives retries
Tests, CI checks, logs, review gates, or source evidence decide whether it loops again.
Stop condition is explicit
The agent stops when checks pass or reports a real blocker with evidence.
Copy a loop your agent can self-pace
Browse the complete loop directoryUse-case paths for agent work that repeats
These are crawlable category entry points, not decorative tags. Pick the job, then inspect the loops and their verification gates.
Browse CI agent loops
Closed-loop loops for pull requests, failing checks, CI logs, and green builds.
Browse Testing agent loops
Agent loops that run tests, isolate failures, fix regressions, and stop only when verification passes.
Browse Review agent loops
Self-review and independent verification loops for safer AI-generated code changes.
Browse Security agent loops
Security, dependency, secret scanning, and safe remediation loops for AI coding agents.
Browse DevOps agent loops
Deployment, environment, rollback, and Cloudflare/Vercel verification loops.
Browse SEO agent loops
Google SEO, structured data, sitemap, internal linking, and AdSense-readiness loops.
Browse Docs agent loops
Documentation sync, README, AGENTS.md, and project context loops.
Browse Database agent loops
Database migration, D1 schema, seed, and rollback review loops.
Channels that feed the library
View all source channelsEvery loop in the directory
Implement a scoped change, open or update a pull request, inspect CI, and continue until all required PR checks pass.
Review an agent-produced change as a skeptical verifier before it is marked done.
Audit title, description, canonical, Open Graph, headings, and indexability for SEO-critical pages.
Run a structured launch review covering build, SEO, policy pages, analytics, sitemap, and deployment verification.
Review generated SEO pages for thin content, duplicate metadata, broken internal links, and missing structured data.
Run the project test suite, fix root causes, and keep iterating until the selected test command passes.
After deployment, check production URL, health routes, metadata, and key user paths before declaring release success.
Diagnose why a page is not indexed by checking robots, sitemap, canonical, status code, content quality, and internal links.
Before committing, run diff hygiene, secrets checks, and the closest validation command.
Scan repository changes for leaked credentials, local env files, and unsafe debug output before publishing.
Check whether a free content/tool site has enough original value, policy pages, navigation, and ad-safe layout for AdSense review.
Review schema and migration changes for destructive operations, D1 compatibility, indexes, and rollback risk.
What users need to know before copying a loop
FAQ content is visible HTML for users and crawlers. It explains the product instead of relying on deprecated FAQ rich-result treatment.
- What is an agent loop?
- An agent loop is a repeatable workflow that tells an AI agent what to discover, what to change, how to verify the result, and when to stop.
- How is this different from a prompt library?
- A prompt asks for one output. A loop defines the feedback cycle: goal, context, action, checks, failure handling, and exit condition.
- Can I copy the full Markdown page?
- Yes. Loop detail pages expose kickoff prompts and Markdown exports so the complete page context can travel into your agent session.
- Are these loops tied to one coding agent?
- No. Each loop lists supported agents such as Cursor, Claude Code, Codex, Gemini CLI, and OpenCode, with portable instructions.
Agent loop directory by category
Start with a category, an agent, or a source channel, then open the loop detail page to inspect the chain.
Use cases
Agents