phase6-start

phase6-start is a command for Claude Code from kota1026/quantum-shield. It costs 0 tokens per session (724 once invoked), scanned A, original, MIT.

A command for starting phase 6 of a project workflow. It checks progress, finds the first unfinished screen, reads required design files, and verifies supporting infrastructure.

In plain words
What is it for?
Use it to inspect phase progress, identify pending UI work, load design and styling references, check PostCSS, and locate the matching HTML mock.
Why use it?
It gathers the project context needed before implementing the next unfinished screen.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/kota1026/quantum-shield/phase6-start
Clone the repo
git clone --depth 1 https://github.com/kota1026/quantum-shield

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for phase6-start

README.md
[![agentmods](https://agentmods.dev/badge/commands/kota1026/quantum-shield/phase6-start.svg)](https://agentmods.dev/commands/kota1026/quantum-shield/phase6-start)
Your own site
<a href="https://agentmods.dev/commands/kota1026/quantum-shield/phase6-start"><img src="https://agentmods.dev/badge/commands/kota1026/quantum-shield/phase6-start.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 724 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00724
Opus 5 $0.00000 $0.00362
Sonnet 5 $0.00000 $0.00145
Haiku 4.5 $0.00000 $0.00072

Measured 3d ago against content hash 2d61ec89e516, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phase6-start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/phase6-start.md · 71 lines

What it actually says

Phase 6 $ARGUMENTS 開始

今すぐ以下を実行してください(指示ではなく、実際に実行):

STEP 1: 進捗状況を確認

docs_new/01_phase/06_phase6/PHASE6_PROGRESS.md を読み込み、$ARGUMENTS システムの進捗状況を確認してください。

STEP 2: 未完了画面を特定

PHASE6_PROGRESS.md から以下を分析:

  • Status が「Pending」または「In Progress」の画面を特定
  • 未完了画面の中で最初の画面番号を確認
  • その画面名と必要な実装項目(UI, A11y, E2E, Persona Test, PIR)を把握

STEP 3: 必須ファイルを読み込む

以下のファイルを今すぐ並列で読み込んでください:

  1. docs_new/01_phase/04_phase4/01_design/assets/design-concept-5-japan-premium.html
  2. apps/web/tailwind.config.ts
  3. apps/web/src/styles/globals.css
  4. docs_new/02_agents_prompt/02_prompts/30_ui_impl.md

STEP 4: インフラ確認

apps/web/postcss.config.js が存在するか確認し、無ければ作成。

STEP 5: 対象モック確認

docs_new/01_phase/04_phase4/01_design/system_*$ARGUMENTS*/wip/mocks/ から、STEP 2 で特定した未完了画面に対応するHTMLファイルを確認。

STEP 6: 初期化完了報告

以下の形式で報告を出力:

## Phase 6 初期化完了

### 進捗確認結果
- PHASE6_PROGRESS.md: ✅ 読み込み完了
- 対象システム: $ARGUMENTS
- 完了済み画面数: {completed}
- 未完了画面数: {pending}

### 次に実装する画面
- 画面番号: {screen_number}
- 画面名: {screen_name}
- 未完了項目: {UI/A11y/E2E/Persona Test/PIR}

### 読み込んだファイル
- design-concept-5-japan-premium.html: ✅
- tailwind.config.ts: ✅
- globals.css: ✅
- 30_ui_impl.md: ✅

### インフラ検証
- postcss.config.js: ✅ 存在

STEP 7: 未完了画面の実装開始

初期化完了報告を出力後、STEP 2 で特定した未完了画面のUI実装を開始してください。


重要:

  • このコマンドを受けたら、上記を説明せずに実行してください。
  • 必ず PHASE6_PROGRESS.md を確認し、未完了の画面から順番に実装を進めてください。
  • 既に完了している画面は飛ばし、効率的に進めてください。
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 71 lines · 0 tokens per session scan A 2d61ec89e516

Subscribe to this mod's changes

phase6-start is a command published in the GitHub repository kota1026/quantum-shield (0 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 724 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.