Loop Library

Loop Library has two separate but related parts in this repository:

Part	What it is	Where it lives
Loop Library website	The public catalog where people and agents can browse published loops, read them, and copy their prompts. No installation is required.	Live website · shell in site/, database and rendering in worker/
Loop Library skill	An optional installable guide that helps an AI agent find, audit, repair, adapt, or design loops through conversation. It uses the website's live catalog when recommending published loops.	source in skills/loop-library/

The website is the library; the skill is a companion way to work with it. You can browse or give an agent the website without installing the skill. Installing the skill adds the guided workflow, but it does not install or host the website.

Agents that do not have the skill can use the published agent guide, agent instructions, JSON catalog, or plain-text catalog directly.

Each published loop tells an agent what to do, how to check its work, what to try next, and when to stop.

What is a loop?

Most prompts ask an agent to do something once. A loop gives the agent a way to learn from the result and take the next useful step.

For example, a one-shot prompt might say:

Make this website faster.

A loop adds the feedback that makes the work repeatable:

Find the slowest page, make one focused improvement, and measure it again. Keep the change only if it helps. Repeat until every page meets the target or another pass stops producing a meaningful improvement.

Think of a loop as a playbook with feedback built in. It is useful when the first attempt probably will not be the final answer, such as fixing production errors, improving test coverage, reviewing a product, or keeping documentation current.

A good loop answers four simple questions:

• What is the agent trying to accomplish?
• How will it know whether the latest attempt worked?
• What should it do with what it learned?
• When should it finish or ask for help?

Why loops are powerful

AI agents can move quickly, but an open-ended instruction like "keep improving this" leaves too much room for guessing. A loop gives the work a clear finish line and a consistent way to judge progress.

That makes the work easier to trust and easier to repeat. The agent can compare results instead of relying on confidence, keep improvements instead of merely making changes, and stop when it succeeds or stops making progress. The same loop can also be reused by another person or agent without rebuilding the workflow from scratch.

Loops are not permission for an agent to run forever. The best ones are deliberately bounded. They include a real check, a clear stopping point, and a moment to hand control back to a person when judgment or approval is needed.

What the Loop Library skill does

The Loop Library skill gives your agent direct access to the ideas in the library. You can use it to:

• Find a published loop that fits what you are trying to get done.
• Audit an existing loop for weak checks, unsafe actions, or unclear stopping behavior, then repair only the material problems.
• Adapt a useful loop to your tools, limits, and definition of success.
• Design a new loop through a short, plain-language conversation.
• Turn the result into a compact prompt you can use right away.

The skill checks the live catalog when it recommends a published loop. It does not quietly start schedules, change production, or send messages on your behalf. Those actions still require the normal permissions and approvals.

Install the skill

You need Node.js and npx. Pick the platform you use:

Platform	Install command
Codex	npx skills add Forward-Future/loop-library --skill loop-library --agent codex -g -y
Cursor	npx skills add Forward-Future/loop-library --skill loop-library --agent cursor -g -y
Claude Code	npx skills add Forward-Future/loop-library --skill loop-library --agent claude-code -g -y

To install it for all three at once:

npx skills add Forward-Future/loop-library \
  --skill loop-library \
  --agent codex \
  --agent cursor \
  --agent claude-code \
  -g -y

Using another agent? Run the interactive installer and choose from the agents it detects:

npx skills add Forward-Future/loop-library --skill loop-library -g

The command parts mean:

• Forward-Future/loop-library is the GitHub repository to install from.
• --skill loop-library selects this skill from the repository.
• --agent ... selects the agent that should receive it.
• -g makes it available in all your projects. Leave -g off to install it only in the current project.
• -y accepts the install prompts. Leave it off if you want to review the choices interactively.

If an agent was already open and the skill does not appear, restart that agent.

Invoke the skill

The slash-command experience differs slightly by platform:

• Codex: type /skills, choose Loop Library, then enter your request. You can also mention it directly with $loop-library.
• Cursor: type / in Agent chat, search for loop-library, select it, and add your request. You can also type /loop-library directly.
• Claude Code: type /loop-library followed by your request.

You can also describe a matching task normally. These agents can load the skill automatically when your request clearly calls for it, but explicit invocation is the most predictable way to start.

Use Loop Library

You do not need to know loop terminology. Invoke the skill and say what you want to get done. It can take four paths:

Path	What it does	Example request
Find	Searches the live catalog and recommends up to three published loops. It does not run them.	Find a published loop for keeping our documentation current.
Loop Doctor	Audits a loop you paste or name, explains material weaknesses, and repairs only those problems.	Audit this loop and repair only material problems: [paste loop]
Adapt	Tailors a useful loop to your real tools, limits, schedule, and definition of success.	Adapt the Overnight Docs Sweep to this repository and our existing checks.
Design	Asks a few plain-language questions, then creates a short, bounded loop when the catalog has no good fit.	Help me design a loop that turns customer feedback into verified fixes.

For example, in Claude Code or Cursor:

/loop-library Find a loop for improving test reliability.

In Codex, choose Loop Library from /skills, then send:

Find a loop for improving test reliability.

When the skill finds or creates the right loop, it gives you a prompt to use with your agent. Review any placeholders, then ask the agent to run that prompt in the project you want it to work on. Selecting a loop does not start a schedule, deploy code, delete data, send messages, or grant new permissions; you must request those actions explicitly.

Every published loop also includes a few useful parts:

• Use when explains the problem the loop is meant to solve.
• Prompt is the copy-ready instruction for your agent.
• Verify defines the evidence that proves the work succeeded.
• Steps show the feedback cycle in a more readable form.
• Notes call out practical limits, risks, or setup details.
• Related loops point to nearby workflows that may fit better.

Explore or contribute

Visit the Loop Library to browse published loops, copy one into your own workflow, or submit a loop that has worked well for you.

Loop Library is a Forward Future project and is available under the MIT License.

Notes for maintainers

Publish a loop

Public loops are stored in the catalog database attached to the Cloudflare Worker. Publishing a reviewed loop does not require a GitHub commit or a static site deployment.

Copy worker/examples/loop.json somewhere outside the repository, fill in the record, and run:

LOOP_PUBLISH_TOKEN=... \
  npm --prefix worker run loop:publish -- /path/to/loop.json

The command validates the record and publishes the homepage row, detail page, JSON/Markdown/plain-text catalogs, feed, and sitemap from the same database write. Use --draft to save a non-public record or --archive to remove a record from public responses without deleting its revision history.

The first database-backed release needs one import from the private migration bundle. Loop records and bootstrap data are intentionally not committed to GitHub:

LOOP_PUBLISH_TOKEN=... \
  npm --prefix worker run loops:import -- /private/path/bootstrap.json

Set a long random LOOP_PUBLISH_TOKEN as a Worker secret. The catalog uses a SQLite-backed Durable Object and keeps an append-only revision for every publish. The reviewed bootstrap digest is enforced before the database can be activated.

Create a private backup of the current database with:

LOOP_PUBLISH_TOKEN=... \
  npm --prefix worker run loops:export -- /private/path/catalog-backup.ndjson

Restore that snapshot only into a fresh, empty catalog database:

LOOP_PUBLISH_TOKEN=... \
  npm --prefix worker run loops:restore -- /private/path/catalog-backup.ndjson

Bootstrap and backup files must be owner-only (chmod 600). Exports include drafts, archived records, and complete revision history; keep them outside the repository.

The current Git tree contains the site shell and rendering code, but no published loop records, generated loop pages, catalogs, feed, sitemap, or offline catalog fallback. The legacy catalog and source-attribution metadata were already public and intentionally remain in pre-migration Git history; this migration does not rewrite repository history or disrupt existing clones.

Preview locally

python3 -m http.server 4173 --directory site

Then open http://localhost:4173.

Validate a change

npm ci --prefix worker
node --check site/script.js
node scripts/check.mjs
npm --prefix worker run check
python3 -m json.tool site/.herenow/data.json >/dev/null
python3 -m json.tool scripts/seo-geo-query-benchmark.json >/dev/null
git diff --check

Read AGENTS.md before editing loops or publishing the site. It contains the source-of-truth rules for database publishing, generated responses, form security, and clean-main deployments.