feat(v3.2.107): WebUI 全テスト検証 250 項目を全プロジェクト最終プロンプトに追加 - #263
Merged
Kensan196948G merged 2 commits intoApr 30, 2026
Merged
Conversation
- 新規: Claude/templates/claude/instructions/10-webui-final-verification.md フロントエンド 110 項目（UI描画/レスポンシブ/JS/フォーム/セキュリティ/性能/UX） バックエンド 140 項目（API/DB/セキュリティ/性能/バッチ/監視/障害/AI開発系検証） 合計 250 項目を「残りの時間で…時間許す限りでOK」の導入文付きで格納 - BUILD-StartPrompt.ps1 が ^\d パターンで自動収集 → スクリプト変更不要 - START_PROMPT.md 再ビルド（1190行 / 10ファイル + header + footer） - _header.md 推奨読み込み順に webui-final-verification.md と _footer.md を追記 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
📝 WalkthroughWalkthroughv3.2.107 リリースで、WebUI ベースの最終検証・デバッグチェックリスト（計約250項目）を新規ドキュメントとして追加し、START_PROMPT.md に統合。CHANGELOG・README・_header.md にこの追加とビルド/収集フローの記載を反映しました。 Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Review rate limit: 2/5 reviews remaining, refill in 27 minutes and 41 seconds. Comment |
There was a problem hiding this comment.
Pull request overview
全プロジェクト共通の START_PROMPT.md 末尾に、WebUI（フロント/バック）向けの最終検証チェックリスト（250項目）を自動組み込みできるよう、instructions 分割ファイルを追加し、関連ドキュメントと生成物を更新するPRです。
Changes:
10-webui-final-verification.mdを新規追加（WebUI 最終検証 250項目）- instructions の推奨読み込み順リスト（_header）と
START_PROMPT.md（生成物）を更新 - README/CHANGELOG を v3.2.107 の内容に更新
Reviewed changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| README.md | v3.2.107 のハイライトとバージョン表記を更新 |
| Claude/templates/claude/instructions/_header.md | 推奨読み込み順に webui-final-verification と footer を追記 |
| Claude/templates/claude/instructions/10-webui-final-verification.md | WebUI最終検証チェックリスト（250項目）を追加 |
| Claude/templates/claude/START_PROMPT.md | instructions 追加に伴う生成結果を反映 |
| CHANGELOG.md | v3.2.107 のリリースノートを追記 |
|
|
||
| 残りの時間で以下のテスト検証・デバッグができますか？ | ||
| 時間許す限りでOKです。まずは検証したうえでCTOの判断で実行してみてください。 | ||
| 終了後のコミット、プッシュ、PR、マージを実行してください。 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@Claude/templates/claude/instructions/10-webui-final-verification.md`:
- Line 5: Replace the unconditional "終了後にマージ実行" behavior in the template (file:
10-webui-final-verification.md) with a conditional instruction that only
performs commit/push/PR/merge when verification/CI checks and security scans
have passed; locate the plain text "終了後にマージ実行" and change it to something like
"検証成功時のみマージを実行" (or equivalent), and ensure any surrounding steps reference the
verification step by name so the merge is gated on successful validation.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 0bed318c-327b-4b66-b461-ea03f9698b39
📒 Files selected for processing (5)
CHANGELOG.mdClaude/templates/claude/START_PROMPT.mdClaude/templates/claude/instructions/10-webui-final-verification.mdClaude/templates/claude/instructions/_header.mdREADME.md
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
- GitHub Check: Agent
- GitHub Check: test-and-validate
- GitHub Check: PSScriptAnalyzer
🧰 Additional context used
📓 Path-based instructions (2)
**/*.{js,ts,jsx,tsx,py,java,go,rs,cs,cpp,c,rb,php,md}
📄 CodeRabbit inference engine (CLAUDE.md)
Create GitHub Issues for KPI unmet, CI failures, review findings, TODO/FIXME detection, insufficient tests, or security concerns
Files:
Claude/templates/claude/instructions/_header.mdClaude/templates/claude/instructions/10-webui-final-verification.mdCHANGELOG.mdREADME.mdClaude/templates/claude/START_PROMPT.md
**/README.md
📄 CodeRabbit inference engine (CLAUDE.md)
**/README.md: Record that CI is not yet set up if quality gates (lint, unit test, build, dependency/security scan) are unavailable
Update README.md whenever utilizer-facing features, setup procedures, architecture, or quality gates change
Treat README as external-facing truth; do not publish or use a README that cannot withstand external scrutiny
Files:
README.md
🧠 Learnings (4)
📚 Learning: 2026-04-27T11:33:07.329Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: Claude/templates/claude/CLAUDE.md:0-0
Timestamp: 2026-04-27T11:33:07.329Z
Learning: Applies to Claude/templates/claude/**/README.md : README.md must be kept as the source of truth for external documentation; update when features, setup procedures, architecture, or quality gates change
Applied to files:
Claude/templates/claude/instructions/_header.mdClaude/templates/claude/instructions/10-webui-final-verification.mdClaude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-27T11:33:07.329Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: Claude/templates/claude/CLAUDE.md:0-0
Timestamp: 2026-04-27T11:33:07.329Z
Learning: Applies to Claude/templates/claude/**/README.md : README.md should use clear formatting with tables, icons, and diagrams for accessibility
Applied to files:
Claude/templates/claude/instructions/_header.mdClaude/templates/claude/instructions/10-webui-final-verification.mdClaude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-27T11:33:07.329Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: Claude/templates/claude/CLAUDE.md:0-0
Timestamp: 2026-04-27T11:33:07.329Z
Learning: Applies to Claude/templates/claude/**/*.{ts,tsx,js,jsx,py,java,go,rs,cpp,c,h} : Include English comments in code (日本語での対応・解説はドキュメントで行う)
Applied to files:
Claude/templates/claude/instructions/10-webui-final-verification.mdREADME.mdClaude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-22T08:01:46.016Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-22T08:01:46.016Z
Learning: Applies to **/README.md : Update README.md whenever utilizer-facing features, setup procedures, architecture, or quality gates change
Applied to files:
README.mdClaude/templates/claude/START_PROMPT.md
🔇 Additional comments (3)
README.md (1)
10-11: README のバージョン反映は適切です。v3.2.107 の利用者向け変更が要約され、開発状況のバージョン表記も同期されています。
Also applies to: 30-30
Claude/templates/claude/instructions/_header.md (1)
24-25: 読み込み順の更新は妥当です。新規検証セクションとフッターを順序に反映できています。
CHANGELOG.md (1)
5-24: CHANGELOG 追記内容は明確です。対象ファイル・自動収集動作・適用範囲が具体化されており、リリース履歴として追跡しやすいです。
|
|
||
| 残りの時間で以下のテスト検証・デバッグができますか？ | ||
| 時間許す限りでOKです。まずは検証したうえでCTOの判断で実行してみてください。 | ||
| 終了後のコミット、プッシュ、PR、マージを実行してください。 |
There was a problem hiding this comment.
無条件マージ指示は品質ゲートを迂回するため修正してください。
「終了後にマージ実行」を固定すると、CI/セキュリティ未完了でも merge され得ます。検証成功時のみ に条件化してください。
🔧 修正案
-終了後のコミット、プッシュ、PR、マージを実行してください。
+終了後は、検証結果に応じてコミット・プッシュ・PRを実行してください。
+マージは CI / テスト / セキュリティチェック通過時のみ実行してください。必要なら、この指摘を GitHub Issue 化するための起票文（背景/再現/受け入れ条件つき）をこちらで作成します。
As per coding guidelines "**/*.{js,ts,jsx,tsx,py,java,go,rs,cs,cpp,c,rb,php,md}: Create GitHub Issues for ... review findings ... or security concerns".
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@Claude/templates/claude/instructions/10-webui-final-verification.md` at line
5, Replace the unconditional "終了後にマージ実行" behavior in the template (file:
10-webui-final-verification.md) with a conditional instruction that only
performs commit/push/PR/merge when verification/CI checks and security scans
have passed; locate the plain text "終了後にマージ実行" and change it to something like
"検証成功時のみマージを実行" (or equivalent), and ensure any surrounding steps reference the
verification step by name so the merge is gated on successful validation.
- CHANGELOG.md: v3.2.107 + v3.2.106 両エントリを保持 - README.md: v3.2.107 (最新) に統一、旧バージョン表記を v3.2.106 に修正 - START_PROMPT.md: _footer.md (v3.2.106 6ヶ月制約) + 10-webui-final-verification.md (v3.2.107 250項目) を統合再ビルド (1205行) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@Claude/templates/claude/START_PROMPT.md`:
- Around line 1188-1198: WebUI セクション `#10`
末尾にある「以降、全てをCTOの判断に任せます…設定された時間から5時間作業を厳密に守ってください」などの再掲は、先頭の最上位指令（必須実行）で既に提示されているため冗長で解釈ブレを生みますので、該当の重複ブロックを削除するか、もしこのセクション内限定のルールであれば「このセクション内に適用」などの範囲明示に書き換えてください（参照箇所：最上位指令（必須実行）および
WebUI セクション `#10` の該当ブロック）。
- Around line 11-26: In the recommended load order block replace the incorrect
entry "webui-final-verification.md" with the actual filename
"10-webui-final-verification.md" so the agent can locate the file; update the
list under the "推奨読み込み順" section in START_PROMPT.md to include
"10-webui-final-verification.md" instead of "webui-final-verification.md".
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 8a27dfb7-6035-45bf-8782-cd6ab93eb3e6
📒 Files selected for processing (3)
CHANGELOG.mdClaude/templates/claude/START_PROMPT.mdREADME.md
✅ Files skipped from review due to trivial changes (1)
- CHANGELOG.md
🚧 Files skipped from review as they are similar to previous changes (1)
- README.md
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: test-and-validate
🧰 Additional context used
🧠 Learnings (22)
📓 Common learnings
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-30T10:57:03.852Z
Learning: Applies to **/*.test.{js,ts,jsx,tsx} : Add validation checklist Gate-1 execution confirmation to Verify phase of all registered projects
📚 Learning: 2026-04-27T11:33:07.329Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: Claude/templates/claude/CLAUDE.md:0-0
Timestamp: 2026-04-27T11:33:07.329Z
Learning: Required ending processing at 5-hour limit: organize work → minimal commit → push → create PR (Draft ok) → update GitHub Projects → organize test/lint/build/CI results → record restart point → update README.md with summary → final report
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-27T11:33:07.329Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: Claude/templates/claude/CLAUDE.md:0-0
Timestamp: 2026-04-27T11:33:07.329Z
Learning: Applies to Claude/templates/claude/**/README.md : README.md must be kept as the source of truth for external documentation; update when features, setup procedures, architecture, or quality gates change
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-30T10:57:03.852Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-30T10:57:03.852Z
Learning: Applies to **/README.md : Document all README updates when feature functionality, setup procedures, architecture, or quality gates change
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-17T02:53:58.179Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: .github/copilot-instructions.md:0-0
Timestamp: 2026-04-17T02:53:58.179Z
Learning: Follow the standard autonomous development loop: Analysis → Main Agent Discussion → Task Decomposition → Agent Assignment → Implementation/Review → Validation → PR/Issue Update → Completion
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-17T02:53:58.179Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: .github/copilot-instructions.md:0-0
Timestamp: 2026-04-17T02:53:58.179Z
Learning: Use custom agents with role-based delegation (Main, Architect, Task, Code Review, Explore, Research, Ops) for autonomous development
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-30T10:57:03.853Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-30T10:57:03.853Z
Learning: Use the Monitor → Build → Verify → Improve loop sequence for autonomous development operations
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-30T10:57:03.853Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-30T10:57:03.853Z
Learning: Update GitHub Projects status at session start/end and after each loop completion
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-27T11:33:07.329Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: Claude/templates/claude/CLAUDE.md:0-0
Timestamp: 2026-04-27T11:33:07.329Z
Learning: GitHub Projects status must be updated at session start/end and after each loop completion (Inbox → Backlog → Ready → Design → Development → Verify → Deploy Gate → Done/Blocked)
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-27T11:33:07.329Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: Claude/templates/claude/CLAUDE.md:0-0
Timestamp: 2026-04-27T11:33:07.329Z
Learning: STABLE status requires all of: test success, lint success, build success, CI success, review OK, security OK, error count = 0
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-30T10:57:03.853Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-30T10:57:03.853Z
Learning: Allocate token budget across development phases: Monitor 10%, Development 35%, Verify 25%, Improvement 15%, Debug/Repair 10%, Release/Report 5%
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-27T11:33:07.329Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: Claude/templates/claude/CLAUDE.md:0-0
Timestamp: 2026-04-27T11:33:07.329Z
Learning: Merge to main is only permitted after CI success, Codex review approval, and STABLE status (all test/lint/build/security checks passing with zero errors)
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-17T02:54:18.581Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-04-17T02:54:18.581Z
Learning: STABLE status requires all of: install/lint/test/build/CI pass, zero errors, zero security issues
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-30T10:57:03.853Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-30T10:57:03.853Z
Learning: Use workspace-based parallel development with 1 Issue = 1 WorkTree; avoid direct main push
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-30T10:57:03.853Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-30T10:57:03.853Z
Learning: Prohibit direct push to main branch; require branch or WorkTree with PR and CI success
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-27T11:33:07.329Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: Claude/templates/claude/CLAUDE.md:0-0
Timestamp: 2026-04-27T11:33:07.329Z
Learning: main branch direct push is prohibited; all changes must use branch or WorkTree with PR
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-27T11:33:07.329Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: Claude/templates/claude/CLAUDE.md:0-0
Timestamp: 2026-04-27T11:33:07.329Z
Learning: Use Codex normal review for standard changes; use Codex adversarial review for auth/authz changes, DB schema changes, parallel processing additions, and pre-release verification
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-30T10:57:03.853Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-30T10:57:03.853Z
Learning: Execute Codex review commands (/codex:review --base main --background) before PR creation
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-27T11:33:07.329Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: Claude/templates/claude/CLAUDE.md:0-0
Timestamp: 2026-04-27T11:33:07.329Z
Learning: Use CodeRabbit CLI for static analysis complement to Codex: run `/coderabbit:review committed --base main` before PR creation and `/coderabbit:review all --base main` during Verify phase
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-17T02:54:18.581Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-04-17T02:54:18.581Z
Learning: Use `adversarial-review` command for authentication, authorization, database schema changes, parallel synchronization, and pre-release validation only; avoid using on trivial diffs
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-17T02:54:18.581Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-04-17T02:54:18.581Z
Learning: Pull Request required for all changes; CI must pass before merge to `main`
Applied to files:
Claude/templates/claude/START_PROMPT.md
📚 Learning: 2026-04-17T02:54:18.581Z
Learnt from: CR
Repo: Kensan196948G/ClaudeCode-StartUpTools-New PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-04-17T02:54:18.581Z
Learning: Use `review` command before PR creation and updates; use it as the standard for code review instead of single-agent judgment
Applied to files:
Claude/templates/claude/START_PROMPT.md
Comment on lines
11
to
26
| ## 📁 推奨読み込み順 | ||
|
|
||
| ```text | ||
| 00-header.md | ||
| 01-session-startup.md | ||
| 02-core-architecture.md | ||
| 03-state-json-spec.md | ||
| 04-agent-teams.md | ||
| 05-codex-debug.md | ||
| 06-ci-automation.md | ||
| 07-ai-dev-factory.md | ||
| 08-operations.md | ||
| 09-termination-reporting.md | ||
| 10-itsm-integration.md | ||
| 11-memory-and-docs.md | ||
| 12-anti-patterns.md | ||
| _header.md | ||
| session-startup.md | ||
| core-architecture.md | ||
| state-json-spec.md | ||
| agent-teams.md | ||
| codex-debug.md | ||
| github-actions-ci-manager.yml | ||
| ai-dev-factory.md | ||
| operations.md | ||
| termination-reporting.md | ||
| webui-final-verification.md | ||
| _footer.md | ||
| ``` |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Verify START_PROMPT.md の推奨読み込み順にあるファイル名が実在するか
set -euo pipefail
# instruction配下（不明ならまず該当ディレクトリを探索）
fd -a -t f "webui-final-verification.md" .
fd -a -t f "10-webui-final-verification.md" .
# 併せて START_PROMPT.md が参照している行も確認
rg -n "webui-final-verification\.md|10-webui-final-verification\.md" Claude/templates/claude/START_PROMPT.mdRepository: Kensan196948G/ClaudeCode-StartUpTools-New
Length of output: 290
推奨読み込み順のファイル参照を修正が必須
Line 24 で webui-final-verification.md と記載されていますが、実際のファイル名は 10-webui-final-verification.md です。リポジトリに webui-final-verification.md は存在せず、エージェントが該当ファイルを見つけられず手順が崩れます。
修正案
```text
_header.md
session-startup.md
core-architecture.md
state-json-spec.md
agent-teams.md
codex-debug.md
github-actions-ci-manager.yml
ai-dev-factory.md
operations.md
termination-reporting.md
- webui-final-verification.md
+ 10-webui-final-verification.md
_footer.md</details>
<details>
<summary>🤖 Prompt for AI Agents</summary>
Verify each finding against the current code and only fix it if needed.
In @Claude/templates/claude/START_PROMPT.md around lines 11 - 26, In the
recommended load order block replace the incorrect entry
"webui-final-verification.md" with the actual filename
"10-webui-final-verification.md" so the agent can locate the file; update the
list under the "推奨読み込み順" section in START_PROMPT.md to include
"10-webui-final-verification.md" instead of "webui-final-verification.md".
</details>
<!-- fingerprinting:phantom:triton:puma:c4c441fa-8136-47d7-b324-53d9177790c6 -->
<!-- 4e71b3a2 -->
<!-- This is an auto-generated comment by CodeRabbit -->
Comment on lines
+1188
to
+1198
| 以降、全てをCTOの判断に任せます。CTO全権委任で自律開発を続けてください。 | ||
| 設定された時間から5時間作業を厳密に守ってください。 | ||
| 設定された時間を確認してください。 | ||
| 設定された時間内でのMonitor、Development、Verify、Improvementをループ（ループ回数はCTO判断でOKです。）で進めてください。 | ||
| AgentTeams機能を大いに活用してください。 | ||
| Auto Mode による自律開発を実行してください。 | ||
| 全プロセスや状況を可視化してください。 | ||
| ドキュメントファイルも常に確認・更新してください。 | ||
| README.mdは分かりやすく、表とアイコン多用、ダイアグラム図も活用して常に更新してください。 | ||
| GitHub Projectsも常に更新してください。 | ||
|
|
There was a problem hiding this comment.
WebUIセクション末尾で「CTO全権委任/5時間遵守」指示を再掲しており冗長（解釈ブレ要因）
先頭の 最上位指令（必須実行）（Line 65-75）ですでに「以降、全てをCTOの判断に任せます」等が提示されています。
そのうえで WebUI の #10 セクション末尾でも同種の指示が再掲されています（Line 1188-1198）。読み手/エージェント側で「どの範囲に適用する指示か」の解釈が揺れる可能性があるため、末尾の再掲を削除（または “このセクション内は…” のように適用範囲を明示）してください。
✅ 修正案（重複ブロック削除）
- 以降、全てをCTOの判断に任せます。CTO全権委任で自律開発を続けてください。
- 設定された時間から5時間作業を厳密に守ってください。
- 設定された時間を確認してください。
- 設定された時間内でのMonitor、Development、Verify、Improvementをループ（ループ回数はCTO判断でOKです。）で進めてください。
- AgentTeams機能を大いに活用してください。
- Auto Mode による自律開発を実行してください。
- 全プロセスや状況を可視化してください。
- ドキュメントファイルも常に確認・更新してください。
- README.mdは分かりやすく、表とアイコン多用、ダイアグラム図も活用して常に更新してください。
- GitHub Projectsも常に更新してください。📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| 以降、全てをCTOの判断に任せます。CTO全権委任で自律開発を続けてください。 | |
| 設定された時間から5時間作業を厳密に守ってください。 | |
| 設定された時間を確認してください。 | |
| 設定された時間内でのMonitor、Development、Verify、Improvementをループ（ループ回数はCTO判断でOKです。）で進めてください。 | |
| AgentTeams機能を大いに活用してください。 | |
| Auto Mode による自律開発を実行してください。 | |
| 全プロセスや状況を可視化してください。 | |
| ドキュメントファイルも常に確認・更新してください。 | |
| README.mdは分かりやすく、表とアイコン多用、ダイアグラム図も活用して常に更新してください。 | |
| GitHub Projectsも常に更新してください。 |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@Claude/templates/claude/START_PROMPT.md` around lines 1188 - 1198, WebUI
セクション `#10`
末尾にある「以降、全てをCTOの判断に任せます…設定された時間から5時間作業を厳密に守ってください」などの再掲は、先頭の最上位指令（必須実行）で既に提示されているため冗長で解釈ブレを生みますので、該当の重複ブロックを削除するか、もしこのセクション内限定のルールであれば「このセクション内に適用」などの範囲明示に書き換えてください（参照箇所：最上位指令（必須実行）および
WebUI セクション `#10` の該当ブロック）。
Kensan196948G
deleted the
feature/v3.2.107-webui-final-verification-prompt
branch
April 30, 2026 11:00
5 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
10-webui-final-verification.md新規作成: フロントエンド 110 項目 ＋ バックエンド 140 項目（AI 開発系検証含む）の 250 項目を「残りの時間で…時間許す限りでOK」の導入文付きで格納BUILD-StartPrompt.ps1が^\dパターンで新ファイルを自動収集。スクリプト変更なしSTART_PROMPT.md再ビルド: 9ファイル → 10ファイル（1190行）。全プロジェクトの cron・ローカル・SSH 実行で最終指示として適用_header.md更新: 推奨読み込み順にwebui-final-verification.mdと_footer.mdを追記250 項目の構成
Test plan
BUILD-StartPrompt.ps1 -DryRun→10-webui-final-verification.mdが 10 番目に収集されること確認START_PROMPT.mdに「残りの時間で」「AI誤修復確認」が含まれること確認node scripts/validate-state-example.js→ PASSEDnode scripts/check-doc-versions.js→ PASSED (v3.2.107)node scripts/update-readme-stats.js→ no changes影響範囲
全登録プロジェクトの START_PROMPT.md に影響（cron・ローカル・SSH 全実行方式）。
既存の
webui-full-verification-checklist.md（参照ドキュメント）は変更なし。🤖 Generated with Claude Code
Summary by CodeRabbit