Swift-Selena: Command for Claude Code

.claude/commands/save_conversation.md

save_conversation is a command for Claude Code from BlueEventHorizon/Swift-Selena. It costs 0 tokens per session (1,195 once invoked), scanned A, original, MIT.

A command that records important conversation decisions and lessons in `meta/history/CONVERSATION_HISTORY.md`, moving older details into dated archive files when the history grows.

In plain words
What is it for?
Use it after significant design decisions, bug fixes, rule changes, requirement changes, or important user feedback.
Why use it?
It preserves why choices were made and what went wrong, so useful project knowledge is not lost between sessions.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is BlueEventHorizon/Swift-Selena's own configuration. It tells Claude Code how to work on Swift-Selena itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Swift-Selena configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BlueEventHorizon/Swift-Selena. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/BlueEventHorizon/Swift-Selena/main/.claude/commands/save_conversation.md
Clone the repo
git clone --depth 1 https://github.com/BlueEventHorizon/Swift-Selena

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 save_conversation

README.md
[![agentmods](https://agentmods.dev/badge/commands/blueeventhorizon/swift-selena/save_conversation/github.svg)](https://agentmods.dev/commands/blueeventhorizon/swift-selena/save_conversation)
Your own site
<a href="https://agentmods.dev/commands/blueeventhorizon/swift-selena/save_conversation"><img src="https://agentmods.dev/badge/commands/blueeventhorizon/swift-selena/save_conversation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for save_conversation

Your own site · 80×15
<a href="https://agentmods.dev/commands/blueeventhorizon/swift-selena/save_conversation"><img src="https://agentmods.dev/badge/commands/blueeventhorizon/swift-selena/save_conversation.svg" alt="Reviewed on agentmods" width="80" 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 1,195 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01195
Opus 5 $0.00000 $0.00598
Sonnet 5 $0.00000 $0.00239
Haiku 4.5 $0.00000 $0.00120

Measured 9d ago against content hash 3a30de0a8d94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

save_conversation 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 9d 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/save_conversation.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

対話履歴の保存

検討してきた内容、対話した内容を meta/history/CONVERSATION_HISTORY.md に記録する。


ファイル構成

meta/history/
├── CONVERSATION_HISTORY.md  # 現行ファイル
└── archive/                  # アーカイブ
    └── CONVERSATION_HISTORY_YYYYMMDD.md

運用ルール

項目 基準
サマリー 最大500行(アーカイブした会話から抽出した重要な教訓)
詳細履歴 最大1000行
合計 1500行目安
1500行超過時 古い詳細履歴をarchive/に移動(日付付きファイル名)

重要度ランク(5段階)

ランク 基準 まとめ時
★★★★★ アーキテクチャルール変更、重大バグ修正、私の誤りパターン サマリーに残す
★★★★☆ 設計判断の重要な変更 サマリーに残す
★★★☆☆ 要件変更の経緯 見出しと結論だけ残す
★★☆☆☆ 実装進捗の詳細 アーカイブ候補
★☆☆☆☆ 作業ログ 記録しない

記録すべき内容

記録する 記録しない
設計判断とその理由 単純な作業ログ
バグの根本原因と修正 タスク完了報告({feature}_plan.mdで管理)
ルール追加/変更の経緯 コードの詳細(コード自体を見ればわかる)
ユーザーからの重要な指摘 一時的なエラー対応
私の誤りパターン

書き方のルール [MANDATORY]

1. 対象を必ず明示する

悪い例:

- キーワードインデックス削除
- タスク粒度を合わせる

良い例:

- **docs/docs_toc.md内「キーワードインデックス」セクション**: 削除
- **docs/docs_toc.md内「タスク別リファレンス」**: {feature}_plan.mdの粒度に合わせる

2. 対象の種類

対象 書き方
ファイル全体 **docs/docs_toc.md**:
ファイル内セクション **docs/docs_toc.md内「セクション名」**:
コード **Domain/Service/XxxService.swift**: またはコードブロック内にコメント
ユーザー発言 #### ユーザー指摘(原文) + 引用ブロック

3. ユーザー指摘は原文を引用

#### ユーザー指摘(原文)
> 「Serviceにget関数はいらない。バグの素」
> 「ServiceはStreamで通知すべき」

4. コード例にはファイルパスを記載

// Domain/Service/FooService.swift
private let fooRepository: FooRepositoryType  // Protocol経由でDI注入

ファイル構造

# 対話履歴

このファイルは、プロジェクトにおける重要な設計判断や検討内容の履歴を記録します。

## 重要な教訓(サマリー)

### カテゴリ名 [★★★★★]

- **教訓タイトル**
  - 対象: `ファイルパス` または `ファイル内セクション`
  - 理由: なぜそうすべきか
  - 正解: どうすべきか

---

## 詳細履歴

### YYYY-MM-DD: タイトル [★★★★★]

#### 問題
[何が問題だったか]

#### ユーザー指摘(原文)
> 「引用」

#### 結論
[最終的にどうしたか]

#### 変更内容
- **対象ファイル/セクション**: 変更内容

---

## アーカイブ

詳細な履歴は `archive/` ディレクトリを参照:
- `CONVERSATION_HISTORY_YYYYMMDD.md`

Read the full file on GitHub · 153 lines

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. 9d ago First seen · 153 lines · 0 tokens per session scan A 3a30de0a8d94

Subscribe to this mod's changes

save_conversation is a command published in the GitHub repository BlueEventHorizon/Swift-Selena (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,195 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.