Source-reviewed loops for agents that need feedback gates, not vague one-shot prompts.

Submit an agent loop for review
Agent Loop LibraryClosed-loop workflowsCursor, Claude Code, Codex

Find 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 directory
CImanual trigger Hardened

Ship PR Until Green

Implement a scoped change, open or update a pull request, inspect CI, and continue until all required PR checks pass.

CursorClaude CodeCodex
pull-requestcigithub-actionsverification

Kickoff preview

Take this branch to a green pull request. Implement the requested change, run local verification, open or update the PR, run `gh pr checks`, inspect failures, fix root causes, and repeat until every required check passes or you hit the iteration cap.
Goal: Open or update a pull request and stop only when all required PR checks are green.
Check command: gh pr checks
Exit condition: All required pull request checks are successful and the PR is ready for review or merge.
Max iterations: 10
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not disable required checks, edit loops to skip jobs, or remove tests to make CI green.
- Do not merge the PR unless the user explicitly asked for merge authority.
View
Reviewmanual trigger Hardened

Independent Verifier Pass

Review an agent-produced change as a skeptical verifier before it is marked done.

CursorClaude CodeCodex
reviewverificationquality

Kickoff preview

Act as an independent verifier. Restate the requirements, inspect the diff, run relevant checks, and return a pass/fail/blocker verdict with evidence.
Goal: Prove the implementation satisfies the request without relying on the implementer’s claim.
Check command: git diff --stat && git diff --check
Exit condition: The verifier can map each requirement to code and verification evidence.
Max iterations: 3
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not rubber-stamp. Find at least one plausible failure mode and check it.
View
SEOmanual trigger Hardened

SEO Metadata Audit Loop

Audit title, description, canonical, Open Graph, headings, and indexability for SEO-critical pages.

CursorClaude CodeCodex
seometadatacanonicalssr

Kickoff preview

Audit SEO metadata from server-rendered HTML for the target pages. Verify title, description, canonical, H1, Open Graph, and indexability, then fix and re-check.
Goal: Ensure SEO-critical pages have unique, server-rendered metadata and indexable content.
Check command: curl -sL $URL | head -80
Exit condition: Each target page has unique title, description, canonical, visible H1, and no accidental noindex.
Max iterations: 5
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not rely only on client-rendered metadata for SEO-critical pages. Verify server HTML.
View
Planningmanual trigger Hardened

Launch Checklist Loop

Run a structured launch review covering build, SEO, policy pages, analytics, sitemap, and deployment verification.

CursorClaude CodeCodex
launchchecklistseodeploy

Kickoff preview

Run a launch readiness checklist: build, deployed critical pages, SEO metadata, sitemap, robots, policy pages, analytics/ads, and final blockers.
Goal: Avoid launching with broken routes, missing policy pages, bad metadata, or unverifiable deployment.
Check command: pnpm build
Exit condition: Build, deployment, SEO basics, policy pages, and critical user paths pass review.
Max iterations: 4
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not mark launch-ready with missing policy pages or broken critical routes.
View
SEOmanual trigger Hardened

Programmatic SEO Page QA Loop

Review generated SEO pages for thin content, duplicate metadata, broken internal links, and missing structured data.

CursorClaude CodeCodex
programmatic-seoqualitythin-content

Kickoff preview

Audit a sample of generated SEO pages for uniqueness, helpfulness, metadata, internal links, and schema. Fix template/data issues before publishing at scale.
Goal: Ensure template-generated pages provide distinct value and are safe to index.
Check command: curl -sL $URL
Exit condition: Sampled generated pages have unique metadata, useful body content, and valid internal links.
Max iterations: 5
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not create large numbers of thin pages solely to manipulate search ranking.
View
Testingmanual trigger Hardened

Test Until Green

Run the project test suite, fix root causes, and keep iterating until the selected test command passes.

CursorClaude CodeCodexGemini CLIOpenCode
testsregressionfeedback-gate

Kickoff preview

Run the project tests, inspect failures, fix the smallest root cause, and repeat until the test command passes. Do not weaken the tests or change the check command.
Goal: Make the selected test command pass without weakening coverage.
Check command: pnpm test
Exit condition: The test command exits successfully with no failing tests.
Max iterations: 8
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not delete, skip, or mark tests as todo unless explicitly requested.
View

Channels that feed the library

View all source channels
34 loops
Curated loop library

Human-reviewed loops with goals, required context, feedback gates, and stop conditions.

Browse curated loops
Source pipeline
Repository discovery

Repository search surfaces real agent workflows before they become copy-ready loops.

Review repository loop candidates
New channel
X social discovery

Social search can capture emerging loop-engineering patterns for editorial review.

Open source channels
01
Open Ship PR Until Green loop

Implement a scoped change, open or update a pull request, inspect CI, and continue until all required PR checks pass.

CursorClaude CodeCodex
02
Open Independent Verifier Pass loop

Review an agent-produced change as a skeptical verifier before it is marked done.

CursorClaude CodeCodex
03
Open SEO Metadata Audit Loop loop

Audit title, description, canonical, Open Graph, headings, and indexability for SEO-critical pages.

CursorClaude CodeCodex
04
Open Launch Checklist Loop loop

Run a structured launch review covering build, SEO, policy pages, analytics, sitemap, and deployment verification.

CursorClaude CodeCodex
05
Open Programmatic SEO Page QA Loop loop

Review generated SEO pages for thin content, duplicate metadata, broken internal links, and missing structured data.

CursorClaude CodeCodex
06
Open Test Until Green loop

Run the project test suite, fix root causes, and keep iterating until the selected test command passes.

CursorClaude CodeCodexGemini CLIOpenCode
07
Open Deploy Verification Loop loop

After deployment, check production URL, health routes, metadata, and key user paths before declaring release success.

Claude CodeCodexGemini CLIOpenCode
08
Open GSC Indexing Debug Loop loop

Diagnose why a page is not indexed by checking robots, sitemap, canonical, status code, content quality, and internal links.

CursorClaude CodeCodex
09
Open Pre-Commit Guard loop

Before committing, run diff hygiene, secrets checks, and the closest validation command.

Claude CodeCodexGemini CLIOpenCode
10
Open Secret Leak Scan Loop loop

Scan repository changes for leaked credentials, local env files, and unsafe debug output before publishing.

Claude CodeCodexGemini CLIOpenCode
11
Open AdSense Readiness Audit loop

Check whether a free content/tool site has enough original value, policy pages, navigation, and ad-safe layout for AdSense review.

CursorClaude CodeCodex
12
Open Database Migration Review loop

Review schema and migration changes for destructive operations, D1 compatibility, indexes, and rollback risk.

CursorClaude CodeCodex

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.