Prompt-Sammlung
50 Loop-Prompts für Claude Code
Architecture Satisfaction Loop
Code-QualitätFür gezieltes Architektur-Refactoring, bei dem du das Ziel konkret beschreiben kannst und nach jeder Änderung live testen willst. Verbindet Live-Tests, unabhängige Reviews und Checkpoint-Commits, um das Risiko des Refactorings zu senken.
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.Clodex Adversarial Review Loop
Code-QualitätFür relevante Code-Änderungen, die von unabhängigem Review profitieren und mehrere strukturierte Review-and-Fix-Runden brauchen. Trennt Builder- und Reviewer-Rolle und schafft einen begrenzten Repair-Zyklus mit persistentem State für sauber wieder aufnehmbare Läufe.
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.
Devil's Advocate Loop
Code-QualitätVor folgenreichen Designs wie Architekturen, Schnittstellen oder Rollout-Plänen, die von strukturiertem Gegen-Review mit dokumentierten Einwänden und evidenzbasierter Auflösung profitieren.
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.
Customer AI Deployment Loop
Deployment & OpsWenn ein KI-Workflow innerhalb eines echten Kundenprozesses laufen muss und Validierung, Freigabe, schrittweisen Rollout, Monitoring und messbare Business-Ergebnisse braucht.
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.
Product Update Podcast Loop
ContentWenn ein Produkt häufig genug neue Features veröffentlicht, dass Nutzer von wiederkehrenden Audio-Erklärungen profitieren. Automatisiert das Umwandeln öffentlicher Produkt-Updates in kurze Podcast-Folgen.
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.
Infinite Clickbait Loop
ContentWenn Videothema und Asset-Set stehen, das Thumbnail aber mehrere strukturierte Runden Ideation und Bewertung braucht, bevor die Produktion startet.
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.
War Loops Frontend Designer
Frontend & VisualWenn ein Frontend aus einer URL oder einem Bild rekonstruiert werden muss und die Treue über Aussehen, Bewegung und responsives Verhalten gemessen werden soll, nicht aus einem einzigen Screenshot beurteilt.
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.
Boeing 747 Benchmark
Frontend & VisualAls visueller Benchmark für einen Agenten, der eine komplexe Three.js-Szene baut, eigene Renderings inspiziert und das Ergebnis über wiederholtes Vision-Feedback verbessert. Das Kamerasystem verwandelt visuelles Urteil in einen wiederholbaren Feedback-Loop.
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.
Fresh Clone Loop
DokumentationUm zu verifizieren, dass die Onboarding-Anleitung eines Repositories für neue Mitwirkende wirklich funktioniert, indem du wiederholt in saubere Umgebungen klonst und Dokumentations-Lücken und versteckte Annahmen schließt, bis ein einziger ununterbrochener Lauf gelingt.
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.
Self-Improving Champion Loop
OptimierungUm einen Prompt, eine Policy, eine Konfiguration oder ein anderes testbares Artefakt zu verbessern, wenn günstige Iteration wertvoll ist, die finale Akzeptanz aber frische Evidenz braucht, um Overfitting zu verhindern.
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.
Continuous-Claude Relay Loop
DokumentationWenn du Claude über viele Stunden unbeaufsichtigt laufen lässt und jede Iteration ihren Kontext sauber an die nächste übergeben soll. Die Staffel-Metapher verhindert, dass Claude das ganze Feature in einem Pass umschreibt und beim Iterationslimit Fortschritt verliert.
We are building... You should pick one thing to work on from SPEC.md, just one, and read SHARED_TASK_NOTES.md for the current status. If it's bigger than a single focused task, break it into small subtasks and only do the first one. Before you start, jot the breakdown into SHARED_TASK_NOTES.md so the next developer knows what's done, what's in flight, and what's queued. Work the one small piece end-to-end (build, test, verify it actually runs), then update SHARED_TASK_NOTES.md with where you left off, what's next, and any decisions or gotchas worth handing over. This is a relay so don't try to land the whole feature yourself. Leave the baton somewhere obvious for the next dev to grab (no need to commit or push).
Anthropic Ralph-Loop Plugin
Code-QualitätFür gut definierte Aufgaben mit klaren Erfolgskriterien, die von Iteration und automatischer Verifikation (Tests, Linter) profitieren. Das offizielle Anthropic-Plugin formalisiert das Ralph-Pattern mit einem Completion-Promise als sauberer Stop-Bedingung und einem harten Iterations-Cap.
/ralph-loop "Build a REST API for todos. Requirements: CRUD operations, input validation, tests. Output <promise>COMPLETE</promise> when done." --completion-promise "COMPLETE" --max-iterations 50
Kill Flaky Tests Loop
Code-QualitätWenn die CI gelegentliche Test-Fehlschläge zeigt und du nicht unterscheiden kannst, welche Tests echt kaputt und welche nur unzuverlässig sind. Der Loop führt die Test-Suite wiederholt aus, bis fünf grüne Läufe hintereinander beweisen, dass die Flaky-Tests behoben oder quarantäniert sind.
/loop run my test suite 20 times, collect every intermittent failure, fix or quarantine the flaky ones, and don't stop until you get 5 consecutive fully-green runs
Auth Tests /goal (offiziell)
Code-QualitätDas kanonische /goal-Beispiel aus Anthropics offizieller Dokumentation. Verwende es, wenn du Claude auf einem fokussierten Test-und-Lint-Slice iterieren lassen willst, bis beide Gates grün sind. Das klarste minimale Template für Einsteiger.
/goal all tests in test/auth pass and the lint step is clean
Changelog Sync (Headless)
DokumentationOffizielles Non-Interactive-Beispiel (Headless), das zeigt, wie du ein /goal in `claude -p` einpackst, sodass der gesamte Loop in einem einzigen Shell-Aufruf zu Ende läuft. Ideal für cron-artige CHANGELOG-Hygiene ohne offene Session.
claude -p "/goal CHANGELOG.md has an entry for every PR merged this week"
Release Branch Maintenance Loop
Deployment & OpsAnthropics offizielles Beispiel für eine projekt-spezifische `.claude/loop.md`, die den eingebauten Maintenance-Prompt ersetzt. Verwende es bei einem langlebigen Release-Branch, der durch ein nacktes `/loop` jede Iteration weitergepflegt werden soll (CI rot, neue Review-Kommentare, ruhiger Status).
Check the `release/next` PR. If CI is red, pull the failing job log, diagnose, and push a minimal fix. If new review comments have arrived, address each one and resolve the thread. If everything is green and quiet, say so in one line.
Dynamic Interval PR Watch
Deployment & OpsOffizielles Beispiel für einen intervall-losen /loop. Claude taktet sich selbst zwischen 1 Minute und 1 Stunde, je nach PR-Aktivität (kurze Wartezeiten, wenn die CI läuft, längere bei Ruhe). Token-effizienteres „Babysit a PR“-Pattern als festes Pollen.
/loop check whether CI passed and address any review comments
Ralph Original One-Liner
Code-QualitätDer Ur-Prompt: ein nackter Bash-`while :; do`, der eine Prompt-Datei in einen Coding-Agenten pipet. Die Technik, die Anthropic später als ralph-wiggum-Plugin ausgeliefert hat. Verwende es, um das Loop-Pattern in der reduziertesten Form zu verstehen; tausche `claude-code` gegen jedes andere Agent-CLI aus.
while :; do cat PROMPT.md | claude-code ; done
Cursed Compiler Loop
Code-QualitätHuntleys tatsächlicher Loop-Body zum Bau der „cursed“-Sprache. Bemerkenswert wegen des Parallel-Subagent-Patterns, des „search before assuming missing“-Guardrails und der vielfach kopierten Anti-Slop-Klausel in Großbuchstaben. Verwende es bei langlaufenden Implementierungs-Grinds mit starkem Anti-Platzhalter-Druck.
0a. study specs/* to learn about the compiler specifications 0b. The source code of the compiler is in src/ 0c. study fix_plan.md. 1. Your task is to implement missing stdlib (see @specs/stdlib/*) and compiler functionality and produce an compiled application in the cursed language via LLVM for that functionality using parrallel subagents. Follow the fix_plan.md and choose the most important 10 things. Before making changes search codebase (don't assume not implemented) using subagents. You may use up to 500 parrallel subagents for all operations but only 1 subagent for build/tests of rust. 2. After implementing functionality or resolving problems, run the tests for that unit of code that was improved. If functionality is missing then it's your job to add it as per the application specifications. Think hard. 2. When you discover a parser, lexer, control flow or LLVM issue. Immediately update @fix_plan.md with your findings using a subagent. When the issue is resolved, update @fix_plan.md and remove the item using a subagent. 3. When the tests pass update the @fix_plan.md`, then add changed code and @fix_plan.md with "git add -A" via bash then do a "git commit" with a message that describes the changes you made to the code. After the commit do a "git push" to push the changes to the remote repository. 999. Important: When authoring documentation (ie. rust doc or cursed stdlib documentation) capture the why tests and the backing implementation is important. 9999. Important: We want single sources of truth, no migrations/adapters. If tests unrelated to your work fail then it's your job to resolve these tests as part of the increment of change. 999999. As soon as there are no build or test errors create a git tag. If there are no git tags start at 0.0.0 and increment patch by 1 for example 0.0.1 if 0.0.0 does not exist. 999999999. You may add extra logging if required to be able to debug the issues. 9999999999. ALWAYS KEEP @fix_plan.md up to do date with your learnings using a subagent. Especially after wrapping up/finishing your turn. 99999999999. When you learn something new about how to run the compiler or examples make sure you update @AGENT.md using a subagent but keep it brief. For example if you run commands multiple times before learning the correct command then that file should be updated. 999999999999. IMPORTANT DO NOT IGNORE: The standard libray should be authored in cursed itself and tests authored. If you find rust implementation then delete it/migrate to implementation in the cursed language. 99999999999999. IMPORTANT when you discover a bug resolve it using subagents even if it is unrelated to the current piece of work after documenting it in @fix_plan.md 9999999999999999. When you start implementing the standard library (stdlib) in the cursed language, start with the testing primitives so that future standard library in the cursed language can be tested. 99999999999999999. The tests for the cursed standard library "stdlib" should be located in the folder of the stdlib library next to the source code. Ensure you document the stdlib library with a README.md in the same folder as the source code. 9999999999999999999. Keep AGENT.md up to date with information on how to build the compiler and your learnings to optimise the build/test loop using a subagent. 999999999999999999999. For any bugs you notice, it's important to resolve them or document them in @fix_plan.md to be resolved using a subagent. 99999999999999999999999. When authoring the standard library in the cursed language you may author multiple standard libraries at once using up to 1000 parrallel subagents 99999999999999999999999999. When @fix_plan.md becomes large periodically clean out the items that are completed from the file using a subagent. 99999999999999999999999999. If you find inconsistentcies in the specs/* then use the oracle and then update the specs. Specifically around types and lexical tokens. 9999999999999999999999999999. DO NOT IMPLEMENT PLACEHOLDER OR SIMPLE IMPLEMENTATIONS. WE WANT FULL IMPLEMENTATIONS. DO IT OR I WILL YELL AT YOU 9999999999999999999999999999999. SUPER IMPORTANT DO NOT IGNORE. DO NOT PLACE STATUS REPORT UPDATES INTO @AGENT.md
Hamel Adversarial Review Loop
Code-QualitätZweistufiger Loop: Claude implementiert, dann startet ein Stop-Hook bis zu vier unabhängige Codex-Review-Agenten (Diff, Holistic, Next.js bei Bedarf, UX und Browser bei Bedarf) und blockt das Beenden, bis die Findings adressiert sind. Für jedes Feature, bei dem du einen unabhängigen Reviewer willst, der Claudes Reasoning nicht gesehen hat.
/review-loop Add user authentication with JWT tokens and test coverage
Slow API Detector Loop
Deployment & OpsLeichtgewichtiger Log-Tail-Loop, der Latenz-Regressionen ohne APM-Stack einfängt. Gutes Beispiel für ein /loop, bei dem der Prompt selbst die Observability definiert (kein MCP, keine zusätzliche Tooling-Schicht).
/loop 10m Check API requests in ./logs/access.log from the last 10 minutes. If the average response time exceeds 2 seconds or if any individual request takes longer than 10 seconds, list the details of the slow requests.
Secrets-in-Diff Scanner Loop
Deployment & OpsKontinuierlicher „habe ich gerade ein Secret geleakt?“-Guard für Solo-Devs ohne bezahlten Secret-Scanner. Stündlicher /loop-Diff-Scan mit reinem Alert-Vertrag, kein Auto-Fix.
/loop 1h scan the git diff from the last hour to check if any API keys, passwords, tokens, or other sensitive information were accidentally committed. Alert me immediately if found
Stale Branch Janitor Loop
DokumentationTägliche Branch-Hygiene-Loop, die sichere Löschvorschläge macht statt sie auszuführen. Gutes Template für „advisory“ /loop-Prompts, bei denen du einen täglichen Schubs willst, aber keine zerstörerische Autonomie.
/loop 24h List all remote branches that haven't been updated in over 30 days, indicate whether they have been merged into main, and suggest which ones can be safely deleted.
Single-Task PRD Ralph Playbook
Code-QualitätDie „eine Task pro Iteration“-Ralph-Variante, getrieben von einer PRD-JSON. Verwende es bei einer langen Spec, die in diskrete Pass-gegated Tasks zerlegt ist, und du strikten Single-Task-pro-Turn-Fokus willst, um das Kontext-Budget scharf zu halten.
You are an autonomous coding agent working on this project. Your task: 1. Read prd.json to find the highest priority task where passes is false 2. Implement that single task 3. Run tests to verify: npm run typecheck && npm test && npm run build 4. If tests pass, update prd.json to set passes: true 5. Append progress to progress.txt 6. Commit your changes with a descriptive message Only work on ONE task per iteration. When ALL tasks in prd.json have passes: true, output <promise>COMPLETE</promise>
Snarktank Ralph PRD Loop
Code-QualitätRyan Carsons kanonische Ralph-PRD-Variante: ein autonomer Agent arbeitet sich Story für Story durch eine PRD-JSON, branchet pro Story, läuft Quality-Checks, committet bei Grün und stoppt erst, wenn alle Stories `passes: true` haben. Spezifische Browser-Verifikation für Frontend-Stories und ein „Codebase Patterns“-Log machen den Loop produktionstauglich.
# Ralph Agent Instructions You are an autonomous coding agent working on a software project. ## Your Task 1. Read the PRD at `prd.json` (in the same directory as this file) 2. Read the progress log at `progress.txt` (check Codebase Patterns section first) 3. Check you're on the correct branch from PRD `branchName`. If not, check it out or create from main. 4. Pick the **highest priority** user story where `passes: false` 5. Implement that single user story 6. Run quality checks (e.g., typecheck, lint, test - use whatever your project requires) 7. Update AGENTS.md files if you discover reusable patterns (see below) 8. If checks pass, commit ALL changes with message: `feat: [Story ID] - [Story Title]` 9. Update the PRD to set `passes: true` for the completed story 10. Append your progress to `progress.txt` ## Progress Report Format APPEND to progress.txt (never replace, always append): ``` ## [Date/Time] - [Story ID] Thread: https://ampcode.com/threads/$AMP_CURRENT_THREAD_ID - What was implemented - Files changed - **Learnings for future iterations:** - Patterns discovered (e.g., "this codebase uses X for Y") - Gotchas encountered (e.g., "don't forget to update Z when changing W") - Useful context (e.g., "the evaluation panel is in component X") --- ``` Include the thread URL so future iterations can use the `read_thread` tool to reference previous work if needed. The learnings section is critical - it helps future iterations avoid repeating mistakes and understand the codebase better. ## Consolidate Patterns If you discover a **reusable pattern** that future iterations should know, add it to the `## Codebase Patterns` section at the TOP of progress.txt (create it if it doesn't exist). This section should consolidate the most important learnings: ``` ## Codebase Patterns - Example: Use `sql<number>` template for aggregations - Example: Always use `IF NOT EXISTS` for migrations - Example: Export types from actions.ts for UI components ``` Only add patterns that are **general and reusable**, not story-specific details. ## Update AGENTS.md Files Before committing, check if any edited files have learnings worth preserving in nearby AGENTS.md files: 1. **Identify directories with edited files** - Look at which directories you modified 2. **Check for existing AGENTS.md** - Look for AGENTS.md in those directories or parent directories 3. **Add valuable learnings** - If you discovered something future developers/agents should know: - API patterns or conventions specific to that module - Gotchas or non-obvious requirements - Dependencies between files - Testing approaches for that area - Configuration or environment requirements **Examples of good AGENTS.md additions:** - "When modifying X, also update Y to keep them in sync" - "This module uses pattern Z for all API calls" - "Tests require the dev server running on PORT 3000" - "Field names must match the template exactly" **Do NOT add:** - Story-specific implementation details - Temporary debugging notes - Information already in progress.txt Only update AGENTS.md if you have **genuinely reusable knowledge** that would help future work in that directory. ## Quality Requirements - ALL commits must pass your project's quality checks (typecheck, lint, test) - Do NOT commit broken code - Keep changes focused and minimal - Follow existing code patterns ## Browser Testing (Required for Frontend Stories) For any story that changes UI, you MUST verify it works in the browser: 1. Load the `dev-browser` skill 2. Navigate to the relevant page 3. Verify the UI changes work as expected 4. Take a screenshot if helpful for the progress log A frontend story is NOT complete until browser verification passes. ## Stop Condition After completing a user story, check if ALL stories have `passes: true`. If ALL stories are complete and passing, reply with: <promise>COMPLETE</promise> If there are still stories with `passes: false`, end your response normally (another iteration will pick up the next story). ## Important - Work on ONE story per iteration - Commit frequently - Keep CI green - Read the Codebase Patterns section in progress.txt before starting
Adam Tuttle RALPH Workflow
Code-QualitätStrikt eine Aufgabe pro Iteration: PRD-Walker, der `npm run check` plus `npm run test` als Gate setzt, und der bei Permission-Problemen explizit `<PROMISE>NEED_PERMISSIONS</PROMISE>` ausgibt statt still zu scheitern. Klare Trennung von Erfolg, Permission-Stopp und „PRD komplett“.
study ./.ralph/prd.json 1. Find the highest-priority item to work on (ignore anything with passes: true) and work only on that item. This should be the one YOU decide has the highest priority - not necessarily the first item in the list. 2. Check that the types check via 'npm run check' (if available) and that the tests pass via 'npm run test' (if available). 3. Update the PRD with the work that was done. 4. Append your progress to the progress.md file. Use this to leave a note for the next person workin in the codebase. 5. Make a git commit of that feature. ONLY WORK ON A SINGLE FEATURE. If, while implementing the feature, you notice the PRD is complete, output <PROMISE>COMPLETE</PROMISE>. If you need additional permissions to complete a task, first double-check that you don't already have the permission. If you have the necessary permission, then proceed to use it. Else print the permissions you need along with <PROMISE>NEED_PERMISSIONS</PROMISE> and exit. I will add them to the .claude/settings.local.json file and re-run.
Downloads Sorter /goal
DokumentationKlassischer Loop-Engineering-Einstieg von Sabrina Ramonov: zählbares Stop-Kriterium („keine Dateien mehr übrig“), explizite Sicherheits-Zäune („nichts löschen“) und ein hartes Turn-Cap. Vorlage für jede repetitive Datei-Organisation, bei der der Exit zählbar ist.
/goal sort every file in my Downloads folder into subfolders by type (Images, Documents, Videos, Other), keep going until no files are left, do not delete anything, and stop after 30 turns.
PDF Summarizer /goal
DokumentationBatch-Zusammenfassung eines ganzen PDF-Ordners in eine einzige Markdown-Datei. Exit ist an „jedes PDF hat eine Zusammenfassung“ gekoppelt, die Quell-PDFs bleiben read-only. Sauberer Vorlage-Pattern für jede Content-Extraktion mit Read-Only-Garantie auf die Originale.
/goal write a 5-line plain-English summary of every PDF in the "reports" folder into summaries.md, keep going until every PDF has a summary, do not edit the PDFs, and stop after 40 turns
Deploy Check Loop (offiziell)
Deployment & OpsDas offizielle Beispiel für einen /loop mit festem Intervall aus Anthropics Dokumentation. Claude prüft alle fünf Minuten, ob ein Deployment fertig ist, und berichtet das Ergebnis. Die einfachste Vorlage für Polling mit klarem Takt.
/loop 5m check if the deployment finished and tell me what happened
Ticket-to-PR-Ready Loop
Code-QualitätWenn ein locker formuliertes Ticket, ein Bug-Report oder eine Kundenbeschwerde zu einer begrenzten Code-Änderung mit genug Belegen für ein schnelles Review werden soll. Der Loop reproduziert den Fehler, belegt die Ursache und liefert den kleinstmöglichen Fix samt Vorher-nachher-Nachweis.
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.
Loop Harness Verification Loop
Deployment & OpsFür wiederkehrende Repository-Aufgaben wie CI-Triage, Issue-Pflege oder Dependency-Updates, die unbeaufsichtigt laufen sollen. Eine Claude-Session erzeugt den Patch, eine zweite prüft ihn gegen explizite Kriterien, damit kein Agent seine eigene Ausgabe freigibt.
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.
Five-Minute Repository Maintainer Loop
Deployment & OpsWenn ein Agent die Wartung mehrerer aktiver Repositories koordinieren soll und die parallele Arbeit steuerbar bleiben muss. Alle fünf Minuten wird der Stand jedes Repository-Threads gelesen, ohne laufende Arbeit zu unterbrechen. Gelandet wird nur mit Tests, Live-Beleg, Autoreview und grüner CI.
While repository maintenance is active, wake every five minutes. Triage [repositories] and read each repository thread's latest state. Reuse one thread per repository; assign its highest-value bounded task only within granted permissions, and do not interrupt coherent active work. Require tests, live proof, autoreview, and green CI before work can land. Escalate product, access, security, or irreversible decisions. Record meaningful changes and stop when every item is landed, decision-ready, blocked, or has no work.
Multi-LLM Convergence Loop
Code-QualitätFür wichtige Pläne, Spezifikationen, Dokumente oder Code-Änderungen, die zwei unabhängige KI-Perspektiven verdienen statt eines Modells, das seine eigenen blinden Flecken prüft. Erst wenn beide Modellfamilien dieselbe unveränderte Fassung freigeben, gilt der Loop als erfolgreich.
Review [plan, specification, document, or code change] against [quality bar] for at most [pass limit] rounds. Have one of two genuinely different model families—AI systems from separate providers—review it. Verify each finding and apply only necessary fixes, then give the revised version to the other reviewer. Succeed only when both approve the same unchanged version. Stop at the limit, repeating disagreement (oscillation), unavailable review, or required approval. Return the final work, round log, verdict, and disagreements.
Goal Forge Loop
DokumentationWenn eine grobe Coding-Idee zu vage für einen langen autonomen /goal-Lauf ist. Der Loop führt ein Interview und schreibt SPEC.md mit messbaren Abschlussprüfungen sowie GOAL.md mit Arbeitsplan und Freigabegrenzen. Fehlt eine Schlüsselentscheidung, gilt das Ziel als nicht bereit.
Turn [rough coding idea] into two planning files before Codex starts /goal, its long-running task mode. Interview the user, then write SPEC.md: what to build, exclude, and consider, plus measurable done_when completion checks. Write GOAL.md: the work plan, progress scorecard, quick and final checks, memory files, evidence, and approval boundaries. If any key decision, permission, tool, environment requirement, or test is missing, stop as not ready. Do not start implementation without approval.
Promise-to-Proof Loop
ContentWenn nicht mehr sicher ist, ob das, was ein Produkt in Marketing, Dokumentation, Demos und KI-Antworten verspricht, noch zum tatsächlichen Verhalten passt. Jedes Versprechen wird als belegt, teilweise belegt, irreführend, unbelegt oder veraltet eingestuft.
List every customer-facing promise [product] makes in marketing, documentation, demos, and AI answers. Compare each promise with current product behavior and evidence, then label it proven, partly proven, misleading, unsupported, outdated, or missing evidence. Fix or narrow the riskiest mismatch and rerun the affected check. Repeat until no high-risk unsupported promise remains. Ask before changing production or public copy. Return the promises, evidence, fixes, and decisions needed.
Propagation Compliance Loop
DokumentationNach einer Änderung, die an mehreren Stellen auftaucht, etwa Versionsnummer, Feature-Name, Zähler oder Regel. Der Loop sucht nach dem alten Wert, behält bewusste Historie und Beispiele und läuft, bis null veraltete Treffer übrig sind. Kehrt einer zurück, wird nach der Quelle gesucht.
After changing a version, count, rule, name, or configuration, list where the new value belongs and update it. Search the project for the old value and related forms. Review each match: fix real stale values, but keep intentional history, examples, migrations, or compatibility rules. Repeat until zero stale values remain. If one returns for two rounds, stop and identify what may be regenerating it. Return changes, intentional matches, and search output.
UI/UX Score Loop
Frontend & VisualFür eine echte Aufgabe wie Registrierung, Login, Onboarding oder Checkout, die sich komplett im Browser durchspielen und konsistent bewerten lässt. Jeder Durchlauf startet ohne gespeicherten Zustand, wird mit einer Checkliste bewertet, und nur regressionsfreie Verbesserungen bleiben.
Improve [user flow, such as signup] at [URL] until [completion criterion]. In a real browser, start each pass from fresh state—no saved login, cookies, or site data. Capture meaningful screens at the agreed sizes and modes, score them with one checklist, and improve the weakest safe area. Rerun the whole flow and keep only regression-free changes. Stop on success, two full passes with no gain, blocked access, or required approval. Return scores, screenshots, changes, and stop reason.
Accessibility Repair Loop
Frontend & VisualWenn eine Website oder App ein definiertes Barrierefreiheitsziel hat, etwa WCAG 2.2 AA, und sich wiederholt mit Scans sowie Tastatur- und Screenreader-Tests prüfen lässt. Jeder Befund wird bestätigt und nach Schaden gewichtet, Prüfungen werden nie stummgeschaltet.
Check [scope] against [accessibility standard, such as WCAG 2.2 AA] with automated scans and available keyboard, screen-reader, and other manual tests. Confirm each issue, rank it by harm, and fix the highest-impact blocker. Rerun the same checks, affected task, and regression tests. Keep only verified fixes. Stop when no blocker remains, progress stalls, verification is unavailable, or approval is required. Never silence a check or weaken the target. Return issues, fixes, evidence, exceptions, and untested needs.
Cold-Load Trimmer Loop
OptimierungWenn eine Web-App beim ersten Besuch zu schwer ist, weil sie vor dem ersten Bildschirm zu viel Code, Styling oder Medien lädt. Ein Kandidat nach dem anderen wird aufgeschoben, komprimiert oder entfernt und nur behalten, wenn Tests bestehen, Screenshots pixelgleich bleiben und die Bytes sinken.
Reduce the data [web app] downloads before its first screen appears. First record passing tests, mobile and desktop screenshots, and compressed transferred bytes—the data actually downloaded. Use the build report only to suggest candidates. Defer, compress, or remove one item, then rebuild and rerun every check. Keep it only if tests pass, screenshots are pixel-identical, and bytes decrease; otherwise revert. Stop when no safe candidate remains, progress stalls, or approval is needed. Return measurements, changes, and untested states.
Housekeeper Loop
Code-QualitätWenn sich in einem Code-Projekt kleine Altlasten angesammelt haben, etwa toter Code, veraltete Dateien, Duplikate oder kaputte Links, breites Löschen aber riskant wäre. Pro Runde wird genau eine risikoarme Aufräumaktion belegt, umgesetzt und mit Build und Tests geprüft.
Review [repository or code project] for dead code, meaning unreachable or unused code; stale files or comments; unused dependencies; duplication; broken links; inconsistent names; and confusing structure. Protect unrelated, active, uncommitted, generated, and uncertain work. Prove one low-risk cleanup, make the smallest coherent change, then rerun the build, tests, runtime checks, and diff review. Keep only verified improvements. Stop when none remain, progress stalls, verification is unavailable, or approval is required. Return changes, evidence, and deferred candidates.
Pixel-Safe CSS Trim Loop
Frontend & VisualWenn Stylesheets ungenutzte Deklarationen, doppelte Regeln oder alte Überschreibungen enthalten könnten und sich repräsentative Seiten per Screenshot vergleichen lassen. Eine Regel pro Runde wird entfernt und nur behalten, wenn alle Screenshots pixelgleich bleiben und das gebaute CSS kleiner wird.
Reduce the CSS styling code [site] sends to users without changing tested screens. First capture representative pages, sizes, themes, and interactions, and record the built CSS size. Treat coverage reports only as suggestions. Remove one declaration or rule, rebuild, and rerun screenshots and project checks. Keep it only if every screenshot is pixel-identical and built CSS is smaller; otherwise revert. Stop when no supported candidate remains, progress stalls, or approval is required. Return reduction, evidence, and untested states.
Prepare-a-New-Project Loop
DokumentationVor dem Bau eines neuen Software-Projekts, wenn Idee oder frühe Dokumente wichtige Entscheidungen noch offenlassen. Pro Runde wird die größte Lücke geschlossen, bis zwei unabhängige Reviewer dieselben Komponenten, dasselbe Datenmodell und dieselbe Definition of Done beschreiben.
Prepare [project] for implementation. Ensure its documents cover requirements, technical design, tasks with acceptance criteria, and test strategy. Each round, fix the largest gap or contradiction that could make two competent engineers build different systems. Keep details traceable, record assumptions, and ask before product forks. Recheck consistency, then have two independent reviewers describe the components, data model, dependencies, and definition of done. Stop when they materially agree and every artifact is testable, or a decision needs the user.
Groundtruth Audit Loop
DokumentationWenn du Sicherheit, Korrektheit oder Betriebsannahmen eines Projekts prüfen willst, bevor du ihm vertraust, und die erste Aufgabe ein Audit statt einer Reparatur ist. Jeder Bereich wird aus dem tatsächlichen Code mit direktem Beleg bewertet, geändert wird erst nach Rückfrage.
Audit [project] from its actual code and configuration, not framework assumptions. For architecture, platform compatibility, security, privileged areas, performance, deployment, jobs, business logic, and code quality, record proved, no issue, weak, or N/A with direct evidence; verify external limits from current primary sources and calculate numbers. Ask before changing code. Stop when every area is logged with severity, or return unverified areas as blocked. Finish with a plain-language overview and area-to-evidence table.
Artifact-to-Skill Loop
OptimierungWenn ein fertiges Ergebnis erfolgreich war, eine wiederholbare Methode enthält und ähnliche Arbeit wieder ansteht. Der Loop destilliert Entscheidungen, Reihenfolge und Prüfungen in einen Skill, lässt ihn an einem frischen zweiten Fall testen und überarbeitet ihn höchstens zweimal.
Turn [artifact] into a skill, playbook, or procedure. Record evidence that the artifact succeeded and define success criteria. Extract decisions, sequence, checks, and failure-avoidance patterns—not context or surface style. Remove sensitive material. Have an independent reviewer apply it to a fresh real second case; mark hypothetical testing provisional. Revise at most twice. Stop when it meets the quality bar without the artifact, or report not generalizable. Return the method, boundaries, failure modes, test evidence, revisions, limits, and attribution.
Error Message Rewrite Loop
ContentWenn ein Produkt rohe, interne oder unverständliche Fehlermeldungen zeigt und die gesamte sichtbare Fehlerfläche kontrolliert neu geschrieben werden soll. Alle Meldungen landen in einer CSV mit Auslöser, Risiko und Prüfstatus, und jede Gruppe wird im echten Browser verifiziert.
Find and improve every user-visible error message within [repository, product, or named scope]. If no scope is supplied, use the user-facing surfaces in the current repository and state any exclusions before editing. Inventory error strings in source code, surfaced API or client errors, and reachable browser states. Record each one in a CSV with its location, trigger, current copy, user risk, proposed replacement, implementation status, and verification result. Rank the errors by user harm. Rewrite one coherent group at a time using plain language and a useful recovery step when one exists. Do not expose provider names, stack traces, internal identifiers, or implementation details. After each change, run the relevant tests, exercise the affected state in a real browser when possible, and search again for raw or internal error text. Do not mark an unreachable state as verified. Stop when every row is verified or explicitly blocked. Finish with the CSV, changed files, test evidence, browser evidence, and blocked items.
Dependency CVE Burndown Loop
Deployment & OpsWenn Dependency-Scans hohe oder kritische CVEs melden und die Behebung davon abhängen soll, ob der verwundbare Code im Projekt tatsächlich erreichbar ist. Gepatcht wird zuerst die riskanteste erreichbare Abhängigkeit, nach Build, Tests und Scan.
Scan the dependencies of [authorized project or current repository] for known CVEs using current advisory sources. If you cannot access the dependency graph, repository, or current advisories, report the blocker and stop. For each high or critical finding, identify the affected direct or transitive dependency, determine whether the vulnerable code is reachable, and check whether the exploit conditions exist in this project. Rank findings by severity, reachability, exposure, and available remediation. Patch or upgrade the highest-risk reachable dependency using the smallest credible change. Run the build, tests, and security scan again. Keep the change only if verification passes and no unacceptable regression appears. Repeat until no exploitable high or critical CVE remains, or every remaining finding has an evidence-backed reachability assessment and an approved risk decision. Ask before major or breaking upgrades, production changes, or accepting risk. Finish with the CVE inventory, reachability evidence, fixes, verification results, and remaining risks.
Dependency Triage Loop
Deployment & OpsWenn mehrere Dependabot-Pull-Requests offen sind und ein befugter Maintainer sie sicher abarbeiten will, ohne veraltete Checks, parallele Merge-Rennen oder automatische Hochrisiko-Upgrades. Der Loop arbeitet einen festen Snapshot ab und merged nur Patch- oder Minor-Updates mit ausdrücklicher Befugnis.
Review every Dependabot pull request currently open in [repository]. Take a fixed snapshot of that set and process each pull request once. Read its diff, release notes, advisories, dependency role, current base revision, and exact-head CI results. Run the repository’s relevant tests in an isolated worktree and classify the update by version change, breaking behavior, security exposure, and regression risk. For failing checks, identify the root cause and prepare the smallest verified repair. Process merges serially: before each merge, refetch the base and pull-request head and require passing exact-head checks. Merge only low-risk patch or minor updates when explicit merge authority has already been granted. Request approval for major, breaking, security-sensitive, uncertain, or externally visible actions. Never push changes, merge, comment, or send messages without the corresponding authority. Stop successfully when the original snapshot is fully processed; stop without changes when none are open; stop as blocked when verification is unavailable. Finish with reviewed, repaired, merged, deferred, and blocked pull requests plus supporting evidence.
Pre-Publish Source Check Loop
ContentUnmittelbar vor der Veröffentlichung eines Artikels, Newsletters oder Reports, dessen Behauptungen, Zitate und Zuschreibungen einen letzten Quellencheck brauchen. Jede prüfbare Aussage wird mit der besten Primärquelle abgeglichen, erfunden wird nie eine Quelle.
Before publishing [draft], inventory every factual, statistical, quoted, or attributed claim a reader could verify. Find the best current primary source for each and label it supported, outdated, misattributed, unsupported, or unverifiable. Fix the riskiest mismatch, then recheck that claim and anything depending on it. Repeat until no high-risk unsupported claim remains or five rounds are exhausted. Never invent a source, cite evidence that does not support the claim, or alter a quotation. Ask before changing a named person’s quote or a legal, medical, or financial statement. Stop without changes if there are no checkable claims; stop as blocked when adequate evidence is unavailable. Finish with the claim-to-source table, corrections made, unresolved claims, and decisions requiring an editor.
Häufig gestellte Fragen
Changelog
Quellenabgleich und Erweiterung auf 50 Loop-Prompts
- Alle Prompts gegen ihre Quellen geprüft; veraltete Fassungen (Forward-Future-Loops, Cursed Compiler, Snarktank Ralph, Adam Tuttle) durch den aktuellen Originalwortlaut ersetzt
- Fünf Prompts entfernt, deren Wortlaut sich in der Quelle nicht belegen ließ
- 22 neue Loop-Prompts mit Quelle ergänzt, darunter Ticket-to-PR-Ready, Dependency Triage, Accessibility Repair und Pre-Publish Source Check
- Offizielles Deploy-Check-Beispiel und Link zum Ralph-Loop-Plugin an die aktuelle Anthropic-Dokumentation angepasst
Erweiterung auf 33 Loop-Prompts
- 5 neue verifizierte Loop-Prompts hinzugefügt
- Ryan Carsons kanonische Ralph-PRD-Variante (snarktank/ralph) mit Browser-Verifikation für Frontend-Stories
- Adam Tuttles RALPH-Workflow mit `NEED_PERMISSIONS`-Escape-Hatch
- Zwei /goal-Patterns von Sabrina Ramonov (Downloads Sorter, PDF Summarizer) mit zählbarem Exit
- Read-Only-First-Week Daily Triage Loop von Cobus Greyling
Erweiterung auf 28 Loop-Prompts
- 18 neue verifizierte Loop-Prompts hinzugefügt
- Vier offizielle Anthropic-Docs-Beispiele für /goal und /loop, plus das offizielle ralph-wiggum Plugin
- Zwei Ralph-Loop-Klassiker von Geoffrey Huntley (Original-One-Liner und Cursed Compiler)
- Adversariales Review-Loop-Pattern von Hamel Husain mit Codex-Subagents
- Verbatim-Prompts von Anand Chowdhary, Eric Zakariasson, Louis Wharmby, Akshay Pachaar, KingBootoshi und mehr
Ältere Versionen anzeigen (1)
Erstveröffentlichung
- 10 kuratierte Loop- und Goal-Prompts aus der Claude-Code-Community
- Sechs Kategorien: Code-Qualität, Deployment & Ops, Content, Frontend & Visual, Dokumentation, Optimierung
- Listen- und Kachelansicht mit Suche, Kategorie-Filter und Sortierung
- Verbatim-Prompts mit Copy-Button, Autor und Quellen-Link