---
title: "Loop Library: Repeatable AI Agent Workflows | Forward Future"
url: https://stacklist.com/card/e7cfddce-55e8-450a-9045-1a58c6da3d22
source_url: "https://signals.forwardfuture.ai/loop-library/"
stack: https://stacklist.com/stack/614ecd6d-12cd-4195-bf9c-3def755c89b2
summary: "Loop Library is a collection of repeatable AI agent workflows with copy-ready prompts for engineering, research, evaluation, and operations tasks. Each loop includes clear verification checks and stopping conditions to guide agents through structured workflows that act on goals, check feedback, and iterate until success criteria are met."
tags: "ai-agents, workflow-automation, prompt-library, agentic-engineering, loop-patterns, agent-loops, verification-checks"
key_entities: "Forward Future (organization), Claude Agent SDK (technology), AI agent loop (concept), ReAct pattern (concept), Matthew Berman (person), Peter Steinberger (person)"
classification: "reference"
content_hash: "sha256:25e55d6ded2233994f10f183554291f928e012ef1e09112091334ac075f6ad27"
acp_version: "0.2"
token_counts_approximate: 5210
visibility: public
agent_accessible: true
status: "final"
---

# Loop Library: Repeatable AI Agent Workflows | Forward Future

Forward Future field guide Loop Library Copy prompts for engineering, research, evaluation, and operations. Each one includes clear checks and tells the agent when to stop. Plain-language definition What is an AI agent loop? An AI agent loop is a repeatable workflow in which an agent acts on a goal, checks what happened, and uses that feedback to choose the next step. It stops when an explicit success or stop condition is met. Loop Library turns that pattern into copy-ready prompts with a clear verification check and stopping point. Sources: Claude Agent SDK loop documentation and the ReAct paper . Agent skill Use Loop Library in your coding agent. Find a published loop or design one directly from your agent. npx skills add Forward-Future/loop-library --skill loop-library -g Copy command View repository Search loops All Engineering Evaluation Operations Content Design Showing 29 loops Updated June 19, 2026 Agentic engineering loops No. Loop Verify / stop Action 001 Engineering By Matthew Berman The docs sweep Keeps documentation aligned with the current codebase and opens a reviewable pull request. Whenever a documentation pass is needed, review the codebase in full and make sure all documentation reflects the current implementation. Update stale documentation, verify the changes, then open a pull request. Verify / stop Documentation matches the current implementation. Finish with a reviewable pull request. Copy 002 Engineering By Peter Steinberger The architecture satisfaction loop Refactors architecture in small, tested, independently reviewed checkpoints. Refactor until you are happy with the architecture. After each significant step, live-test the system, run autoreview, and commit. Track progress in /tmp/refactor-{projectname}.md. Verify / stop The architecture is satisfactory and checks pass. Live-test, autoreview, and commit each significant step. Copy 003 Engineering By Matthew Berman The sub-50 ms page-load loop Optimizes every page until it consistently loads in under 50 ms. Continue optimizing the code for speed. After each significant change, measure page-load performance across every page under the same repeatable test conditions. Continue until every page loads in under 50 ms. Verify / stop Every page loads in under 50 ms. Use the same benchmark and confirm there are no regressions. Copy 004 Engineering By Matthew Berman The production error sweep Finds, fixes, and verifies actionable errors in production. Review our production logs for errors. If you find an actionable issue, trace it to its root cause, fix it, verify the fix, and open a pull request. If no actionable errors are present, stop without making changes. Verify / stop Actionable production errors are fixed and verified. Finish with a PR, or stop when no actionable errors are present. Copy 005 Engineering By Matthew Berman The 100% test coverage loop Adds meaningful tests until the full suite reaches 100% coverage. Add tests until we have 100% test coverage. Verify / stop The full test suite passes at 100% coverage. Use the project's coverage report as the source of truth. Copy 006 Content By Matthew Berman The SEO/GEO visibility loop Fixes the highest-impact gaps in search and AI answer visibility. Run an SEO/GEO audit across crawlability, indexation, page intent, titles, internal links, structured data, source citations, and answer-first content. Rank the gaps by expected impact, fix the highest-leverage issue, then rerun the same crawl and target-query benchmark across search engines and AI answer engines. Repeat until no critical technical issues remain, every priority query maps to a clear answer-ready page, and the benchmark shows no high-impact gap left to fix. Verify / stop Priority pages are indexable, answer-ready, and technically sound. The repeatable crawl and query benchmark finds no remaining high-impact gaps. Copy 007 Engineering By Matthew Berman The logging coverage loop Adds useful, tested logs to every important system path. Review the system's logging and add missing coverage until every important path produces useful, tested logs. Verify / stop Every important path emits useful, tested logs. Representative success and failure tests prove coverage without exposing sensitive data. Copy 008 Engineering By Matthew Berman The nightly changelog loop Keeps the changelog current with meaningful changes from the previous day. Each night, review changes from the previous day and update the changelog with anything users should know. Verify / stop Every user-relevant change from the previous day is accounted for. The changelog is updated and validated, or the no-change result is recorded. Copy 009 Evaluation By Matthew Berman The quality streak loop Fixes product failures until a defined streak of realistic tests passes. Test realistic scenarios. When one fails, document it, add regression and benchmark coverage, fix it, and restart the streak. Stop after [N] successful cases in a row. Verify / stop The latest [N] realistic cases pass in a row. Every earlier failure is documented, fixed, and protected by regression and benchmark coverage. Copy 010 Evaluation By Matthew Berman The full product evaluation loop Tests every major product capability and fixes outcomes below the quality bar. Create [N] realistic scenarios covering every major capability. Before testing, define clear success criteria and choose a consistent evaluation method, such as pass/fail checks or a scoring rubric. Run every scenario under the same conditions and record evidence for each outcome. Fix the underlying cause of anything that does not meet the criteria, rerun the affected scenarios, and then rerun the complete set. Continue until every scenario meets the original quality bar. Verify / stop Every one of the [N] scenarios meets the defined quality bar. The final evaluated run covers every major capability under the original conditions. Copy 011 Engineering By Matthew Berman The test-suite speed loop Speeds up the test suite without weakening coverage, assertions, or isolation. Optimize the test suite to run as quickly as possible without reducing coverage or changing behavior. Verify / stop The suite is faster with no coverage or behavior regression. Repeatable timing, the full passing suite, and the original coverage report prove the result. Copy 012 Engineering By Matthew Berman The repository cleanup loop Recovers valuable repository work and safely removes proven stale state. Inspect local and remote branches, pull requests, commits, and worktrees. Recover valuable work and clean everything stale until the repository is current and organized. Verify / stop Valuable work is recovered and remaining repository state is intentional. Branches, pull requests, commits, and worktrees are current, owned, or safely removed with evidence. Copy 013 Operations By Matthew Berman The stale-safe batch release loop Batches valid changes and releases complete artifacts from the latest integrated main. Review pending changes and pull requests, exclude stale or unfinished work, combine the valid changes, and release them together. Verify / stop Only current, complete changes ship in the combined release. The released revision is the latest integrated main that contains every selected change. Copy 014 Operations By Matthew Berman The production data cleanup loop Removes disallowed production data and prevents the same classification errors from returning. Review production records, remove anything that does not meet the allowed definition, improve the classification logic, and verify the remaining data. Verify / stop Every remaining record meets the allowed definition. Representative classification tests and a post-cleanup audit prove the retained data is valid. Copy 015 Operations By Matthew Berman The post-release baseline loop Benchmarks each completed release and records a reproducible baseline. After current releases finish, run the standard benchmarks and record the results as the new baseline. Verify / stop The new baseline belongs to the completed release. Revision, environment, benchmark version, conditions, and results are recorded together. Copy 016 Engineering By Hiten Shah The ticket-to-PR-ready loop Turns a ticket or complaint into a verified, reviewer-ready pull request. Take a ticket, bug report, failing behavior, or customer complaint and turn it into a review-ready patch. Reproduce the failure in the smallest representative environment, prove the root cause, make the smallest credible fix, and rerun the original reproduction plus relevant regression tests. If the issue cannot be reproduced after two serious attempts, say so. Do not fold unrelated refactors into the patch. Finish with the cause, changed files, before-and-after proof, risks, and pull-request summary. Verify / stop The failure is fixed, verified, and ready for review. The issue reproduces before the fix, no longer reproduces afterward, and relevant regression checks pass. Copy 017 Operations By AgentLed.ai Agent The customer AI deployment loop Moves one customer AI priority through validation, controlled rollout, and monitoring. Run this when a customer requests an AI workflow, reports a failure, or reaches an operations review. Choose one priority, such as enriching leads, drafting emails, summarizing meetings, or updating a CRM. Define the owner, inputs, approvals, success metric, and ROI hypothesis. Dry-run it on realistic customer data, fix the smallest verified problem, then release through approved stages and monitor production. Finish with the outcome, evidence, customer update, lessons saved, and next review. Verify / stop One customer priority reaches a proven terminal state. The workflow reaches its agreed rollout stage, a production issue is fixed, or a blocker is escalated with an owner and next step. Copy 018 Content By Pierson Marks The product update podcast loop Turns meaningful product updates into a short, source-grounded podcast episode. Each night, review publicly released product changes and select only those users need to know. Verify each against the product, docs, or release notes. Use the Jellypod MCP to turn the approved changes into a three-to-five-minute podcast explaining what changed, why it matters, and how to try it. Check the script and audio for accuracy, clarity, and pronunciation. If nothing meaningful shipped, make no episode. Ask before publishing. Finish with the draft episode, sources, and review result. Verify / stop The episode accurately covers every meaningful public update. Finish with a review-ready three-to-five-minute episode, or a confirmed no-episode result when nothing meaningful shipped. Copy 019 Engineering By Lukas Kucinski The Clodex adversarial-review loop Uses Codex to review Claude's pull request until blocking findings are resolved. Run /clodex [task] think hard --max-iter 5 --threshold medium. Claude plans the task, implements it, opens a pull request, asks Codex for an adversarial review, fixes findings above the accepted severity, and repeats. Keep the branch, PR, findings, verdict, and iteration state resumable. Stop when Codex approves, only accepted findings remain, progress stalls, or the iteration cap is reached. Never describe an errored or exhausted run as approved. Finish with the PR, checks, verdict, and remaining findings. Verify / stop The pull request reaches the configured review bar. Codex approves it or only explicitly accepted findings remain; errors, stalls, and exhausted limits are reported as such. Copy 020 Engineering By Istasha The Loop Harness verification loop Ships scheduled agent work only after an independent verification pass. Use Loop Harness for scheduled repository work such as CI triage, issue grooming, dependency updates, or docs sync. Set [retry limit], then start an isolated git worktree. Let one Claude session stage a patch or outbox message and a second Claude session verify it against explicit criteria. Ship only after a pass; otherwise preserve the findings and retry only within the limit. Finish with the source revision, staged output, verifier result, delivery status, and next run. Verify / stop Only independently verified output ships. A second-agent pass releases the configured output; a failed verification preserves evidence and produces no external change. Copy 021 Design By @victormustar The Boeing 747 benchmark Builds and improves a Three.js Boeing 747 across nine repeatable views. Before building, choose reference images, a scoring rubric, [visual threshold], and [budget]. Build the most realistic Boeing 747 you can from Three.js primitives, then create a rig that screenshots nine repeatable angles. After each change, render and score the same views, have a critic identify the weakest feature, and fix it without regressing stronger views. Keep the best version. Stop at the threshold, stalled progress, or budget. Finish with the model, nine renders, scores, remaining gaps, and run summary. Verify / stop The Boeing 747 meets the visual bar from all nine angles. The same camera rig and rubric show every required view meeting the preset threshold, or the run reports stagnation, budget exhaustion, and remaining gaps. Copy 022 Design By Swayam War Loops: frontend reconstruction Reconstructs a real interface and repairs its weakest visual and motion mismatches. Point War Loops at an authorized URL or image. Capture it with a genuine browser and record the layout, styles, content, motion, and responsive behavior. Build a static Pencil mirror and a moving Forge version. Compare both with the source at desktop, tablet, and mobile sizes; repair only the weakest fidelity signals. Stop when every gate passes, progress stalls, or capture is blocked. Finish with the builds, spec, renders, scores, and remaining gaps. Verify / stop The builds match the source across all three fidelity axes. Static appearance, experiential motion, and responsive reflow pass their gates, or the run reports stagnation or a blocked capture. Copy 023 Evaluation By Jose C. Munoz The self-improving champion loop Promotes prompt or policy changes only when they win on fresh holdout cases. Improve a prompt, policy, or configuration. A support assistant's system prompt is one example. Save the champion, its score, a working set, untouched holdout cases, must-pass checks, and [budget]. Each round, change one thing based on a recorded failure. Promote the challenger only if it beats the champion on holdouts by [margin] without weakening a must-pass check; otherwise keep the champion. Stop at the target, budget limit, or no progress. Return the winner, scores, experiment log, and remaining failures. Verify / stop The best holdout-tested champion is returned. Every challenger is logged, and accepted changes beat the previous champion on untouched cases without weakening a must-pass check. Copy 024 Evaluation By Anonymous contributor The devil's-advocate loop Challenges a design until every high-impact objection is resolved or explicitly accepted. Before committing to an architecture, interface, or rollout plan, have a critic argue that it is wrong. Record each objection, impact, and status in a repository-local log at .agent-reviews/redteam.md. The builder must fix and verify each high-impact weakness or document why it is accepted; the critic may reopen unsupported answers. Stop when no high-impact objection remains or the same issues repeat for two rounds without new evidence. Finish with the decision, resolved and accepted objections, evidence, and any stalemate. Verify / stop No high-impact objection remains open. Every logged objection is verified as resolved or explicitly accepted with evidence, or the final report truthfully records a two-round stalemate. Copy 025 Engineering By 0xUmbra The fresh-clone loop Repeats clean onboarding from the README until no hidden setup assumptions remain. Clone [repository] into a disposable environment and follow only its README to the documented ready state, such as running the app or building the package. When a step fails or assumes missing knowledge, record the gap, fix the setup or documentation issue, discard the environment, and start again. Carry no dependencies, configuration, credentials, or repairs between attempts. Stop when one uninterrupted fresh clone reaches that state, progress stalls, or [budget] ends. Return exact commands, gaps closed, and remaining blockers. Verify / stop A clean environment reaches the documented ready state using only the README. The final run uses only the onboarding guide and needs no unstated dependency, configuration, or manual repair. Copy 026 Design By @Alex_FF The Infinite Clickbait thumbnail loop Iterates thumbnail concepts until one clears the quality bar without misleading viewers. For [video], use [approved assets] to make ten thumbnail concepts. Score each at real YouTube sizes against [inspiration channel] for clarity, curiosity, emotional pull, contrast, and accuracy. Take the top three, improve each one's weakest dimension, and rescore them under the same rubric. Keep iterating the strongest concept until it clears [quality threshold] or [budget] ends. Reject anything the video cannot deliver. Return the winner, two runners-up, previews, final scores, and rationale. Verify / stop One accurate thumbnail clears the fixed quality threshold. The winner outscores the alternatives under the same conditions, remains legible at realistic sizes, and represents the video accurately. Copy 027 Engineering By @inferencegod The autonomy-loop builder-reviewer loop Passes code between builder and reviewer until tests prove each accepted fix. Use autonomy-loop for [repository task] after the test, build, and lint gates pass. Run /autonomy-loop:autonomy-init, then start builder and reviewer in separate worktrees. The builder reads LOOP-STATE.md, makes one bounded change, and adds a red-before, green-after test. The reviewer reruns the gates and proves the test by reverting or mutating the fix. Accept only on both passes; park protected or repeated-failure work for a human. Finish with the commit, gate evidence, test proof, trust tier, and risks. Verify / stop Every accepted wave passes autonomy-loop's proof-of-test gate. The new test fails without the change, passes with it, every configured gate passes, and protected production changes remain human-gated. Copy 028 Engineering By 3goblack (@Dis_Trackted) The Codex completion-contract loop Defines completion up front and requires evidence for every reported result. Run $goal-planner-codex [task] for long-running Codex work where partial work could be mistaken for done. Landing a PR and verifying production is one example. Before acting, define every required outcome and its evidence. After each bounded action, mark requirements proved, weak, missing, or contradicted. Complete the Goal only when all are proved; otherwise stop as blocked, stalled, or exhausted. Ask before creating Goal state. Finish with the requirement-to-evidence table, status, owner, and next action. Verify / stop Every Codex Goal requirement has current, adequate proof. The final audit contains no weak, missing, or contradicted required item; otherwise the work remains open, blocked, or exhausted. Copy 029 Evaluation By Agent Zero The Revolve versioned-experiment loop Improves prompts, code, or configurations through comparable, checkpointed experiments. Use Revolve to improve a support prompt, code path, or testable subject. In revolve/, define the goal and [budget], freeze the tests and scoring, checkpoint the current version, and record a baseline. Each round, test one hypothesis; keep only a clear, regression-free win. If the evaluation changes, open a new revision and rerun the baseline. Ask before changing live files. Stop on success, no progress, a blocker, or exhausted budget. Return the best checkpoint, comparisons, rollback, and next action. Verify / stop The best Revolve checkpoint wins within one evaluation revision. The incumbent and candidates have comparable recorded runs, accepted changes pass every guard, rollback is available, and live promotion has approval. Copy No matching loops Try another category, broaden your search, or submit the workflow. Submit a loop A useful loop specifies: trigger, action, proof, memory, and a stopping condition. Weekly picks One useful loop, once a week. Email address Notify me weekly → Company Weekly only. No spam. Unsubscribe anytime. Contribute Share a loop Send the prompt you actually use. We review everything before publishing. Loop title * Name for attribution optional Prompt or instructions * X handle optional Source link optional Company I have the right to share this and understand it may be edited for clarity. Private review queue. Never include secrets or private code. Submit loop →