ループとは正確には何ですか？
ループは、目標、進捗を客観的に検証する検査コマンド、退出条件、最大反復回数の4つで構成される、AI コーディングエージェント向けの再利用可能なワークフローです。起動プロンプトをエージェントに貼り付ければ、退出条件を満たすまで検査コマンドを再実行しながら自律的にタスクを進めます。
Loops
コーディングエージェントがタスクを完了するまで自律的に進められる、再利用可能なプロンプトと段階的なワークフロー。
すべて
品質manual
A11y Audit Until Clean
Run automated accessibility checks on changed routes, fix violations, and repeat until the audit is clean.
Cursor
テストmanual
Build Until Green
Run the production build, fix compile and bundling errors, and loop until the build succeeds.
CursorClaude Code
テストmanual
Coverage Until Threshold
Add focused tests until coverage meets your threshold (e.g. 80%), without changing production behavior unnecessarily.
Claude Code
CIinterval
CI Failure Watcher
Poll CI on an interval, investigate failures when checks go red, and push fixes until green.
CursorClaude Code
CIinterval
PR Babysitter
Every 15 minutes, inspect open PRs with a watch label: nudge reviewers, fix CI, rebase if behind main.
CodexCursor
テストevent
Pre-Commit Guard
Hook that runs tests before git commit commands to block commits when the suite is red.
Cursor
テストmanual
Format Until Clean
Run the formatter, fix any remaining style issues, and loop until the codebase formats cleanly with no diffs.
Cursor
CIinterval
PR Watch Loop
Poll open PRs labeled codex-watch every 15 minutes, review activity, and flag regressions or stale threads.
CodexCursor
テストevent
Post-Edit Test Guard
Hook-based loop that runs related tests after file edits to catch regressions early.
Cursor
テストmanual
Flaky Test Triage
Run failing tests repeatedly, classify each failure as flaky or real, and fix only confirmed regressions.
Claude CodeCursor
CImanual
Ship PR Until Green
Implement on a branch, run tests, push, open a PR, wait for CI, and loop until checks pass and the PR is ready to merge.
Claude CodeCursor
APImanual
OpenAPI Sync Until Valid
Keep openapi.yaml valid and in sync with route handlers — lint the spec and fix drift each pass.
Cursor
APImanual
API Contract Until Match
Loop until API responses match the OpenAPI or JSON Schema contract — catch drift between docs and implementation.
Cursor
メンテナンスmanual
Docs Sync After Edits
After code changes, find affected docs and update README, API references, and inline comments to match.
Cursor
自動化manual
Guardrails Learning Loop
When a check fails twice the same way, append a guardrail sign to .ralph/guardrails.md so the next iteration avoids repeating it.
CursorClaude Code
ドキュメントmanual
Changelog Sync After Ship
After shipping a feature, loop until CHANGELOG.md has a user-facing entry and conventional commits are reflected.
Claude Code
DevOpsinterval
Deploy Verification Loop
On an interval, hit health and smoke endpoints after a deploy until all checks return healthy responses.
CodexCursor
データベースmanual
Migration Until Applied
Run database migrations, fix schema issues, and loop until migrations apply cleanly in dev.
Cursor
メンテナンスmanual
Knip Until Clean
Find and remove dead exports, unused files, and orphan dependencies — loop until knip reports clean.
Cursor
デバッグmanual
Reflexion Debug Loop
On each failed repro attempt, write a short reflection to disk, then retry with that memory — avoids repeating the same wrong fix.
Claude CodeCursor
レビューmanual
De-Sloppify Pass
After implementation, run a cleanup pass: remove debug code, tighten naming, delete dead branches, and align with project conventions.
Claude CodeCursor
テストmanual
Autoloop TDD
Test-first loop: write a failing test, implement the minimum code to pass, refactor, and repeat.
Claude Code
テストmanual
Independent Verifier Pass
When implementation claims done, a separate verifier pass runs build, lint, and tests with no access to the implementer's rationale.
Claude Code
セキュリティmanual
npm Audit Fix Loop
Fix high/critical npm audit findings one at a time with test verification — not a blind npm audit fix --force.
Cursor
CImanual
Fix CI Until Green
Fetch the latest failed CI run, reproduce the failure locally, fix it, and repeat until checks pass.
CursorClaude Code
Gitmanual
Merge Conflict Resolver
Rebase or merge target branch, resolve conflicts file by file, and loop until the branch is current and tests pass.
CursorClaude Code
テストmanual
Lint and Typecheck Fix
Run lint and typecheck, fix reported issues, and loop until the codebase is clean.
Cursor
メンテナンスmanual
Dependency Upgrade One-by-One
Upgrade a single outdated package per iteration, fix breakages, and commit — safer than bulk npm update.
Cursor
自動化manual
Ralph Story Executor
Fresh-context loop: pick one incomplete story from prd.json, implement it, run backpressure checks, commit, and update progress before the next iteration.
CursorClaude Code
メンテナンスinterval
Security Audit Weekly
Weekly npm audit scan, triage vulnerabilities by severity, and propose or apply safe patches.
Claude Code
よくある質問
AI コーディングエージェント向けの再利用可能な Loops に関するよくある質問
通常のプロンプトを書くこととどう違いますか？
通常のプロンプトは1ターンの1つの指示です。ループは繰り返されるターンを取り巻くシステムで、エージェントに自分の作業をどう検証し、いつ停止するかを伝えます。そのため、毎回プロンプトを入力し直さなくても作業を継続できます。この手法は Loop Engineering と呼ばれます。
これらのループはどのコーディングエージェントで使えますか？
このページのほとんどのループは特定のエージェントに依存しません——起動プロンプトはただのテキストなので、Claude Code、Cursor、Codex など任意のコーディングエージェントに貼り付けて使えます。各ループの詳細ページには、専用に構築・テストされたエージェントが記載されています。