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.
npx skills add karaage0703/ai-assistant-workspace --skill xs-diarygit clone --depth 1 https://github.com/karaage0703/ai-assistant-workspaceWrote 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.
[](https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-diary)<a href="https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-diary"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-diary/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.
<a href="https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-diary"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-diary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.01172 |
| Opus 5 | $0.00042 | $0.00586 |
| Sonnet 5 | $0.00017 | $0.00234 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
xs-diary 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 12d 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.
What it actually says
毎日の日記記録スキル
1日を日記形式で記録する。notes/ + Notion の両方に残す。
絶対遵守事項
- 日常の出来事(食事・家族・ペット・散歩・仕事の感想)は必ず記録する
- 日常セクションを開発作業セクションより上に配置する
- ファイル操作なしに「記録した」と報告しない(嘘禁止)
- 完了報告にはNotion日記のURLを含める(Notion連携時)
- 記録にない数値を断定しない。推定する場合は「推定」と明記する
- チャット履歴、memory、notes、必要ならxangi-searchまたは通常のファイル検索で漏れを拾う
保存先
| 場所 | 用途 |
|---|---|
notes/YYYYMMDD_diary.md |
日記本体 |
memory/YYYYMMDD.md |
参考資料(会話ログ・調べたこと) |
| Notion日記DB(任意) | 画像・動画付きリッチ版 |
手順
Step 1: 情報収集
memory/YYYYMMDD.mdを読む(その日の出来事・会話ログ)date -d "YYYY-MM-DD" +%Aで曜日を確認(思い込みで書かない)- 必要に応じて
notes/やxangi-searchで、その日の関連メモ・発信・作業ログを確認する。xangi-search未導入時は通常のファイル検索を使う - チャットプラットフォームで動いている場合は、直近履歴や添付ファイルも確認する
Step 2: notes/に日記作成
notes/YYYYMMDD_diary.md を作成。
Step 3: Notion日記ページ作成(任意)
Notion連携が設定されている場合、notion-manager スキルの notion_tool.py を使って日記ページを作成。
cd skills/notion-manager
# ページ作成
uv run python notion_tool.py diary <DB_ID> -t "YYYYMMDD_タイトル" -d YYYY-MM-DD
# 見出し・本文を追加
uv run python notion_tool.py append <page_id> -H "今日の出来事"
uv run python notion_tool.py append <page_id> -b "内容..."
# 画像アップロード(キャプション付き)
uv run python notion_tool.py upload /path/to/photo.jpg <page_id> -c "キャプション"
Step 4: 同期
git add notes/ memory/ && git commit -m "日記 YYYYMMDD" && git push
Step 5: 完了報告
MM/DDの日記完了!
Notion日記: https://www.notion.so/xxx(Notion連携時)
やったこと:
- ...
notes/ フォーマット
---
tags: [diary]
---
# YYYYMMDD (曜日)
## タイムライン
- HH:MM 出来事
## 食事
- 朝:
- 昼:
- 夜:
## 気づき・学び
## 開発作業
## 気分・体調
## 明日の予定
セクション順序: 日常(タイムライン・食事) → 開発 → その他
書き方の方針
- 事実と感想を分ける
- 食事・運動・睡眠・家族・ペット・外出など、生活ログを開発ログに埋もれさせない
- 数値は記録から直接拾えるものを優先する
- 写真や添付がある場合は、見た内容を短く記録する
- 技術作業は、PR番号・commit・検証結果・次の課題を1〜3行でまとめる
日付ルール
- 0時〜朝5時の作業 → 前日の日記に記録(寝るまでが1日)
完了前チェックリスト
□ `date` コマンドで曜日を確認した
□ 日常セクションに食事・家族・ペット・散歩・仕事を記録した
□ 日常セクションが開発より上にある
□ memory/ にファイル操作で書き込んだ
□ 投稿文は日本語のみ、作業ログ混入なし
□ 推定値と実測値を混同していない
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.
- 12d ago First seen · 128 lines · 84 tokens per session scan A 44a6e3ffd663
xs-diary is a skill published in the GitHub repository karaage0703/ai-assistant-workspace (137 stars, last pushed 24d ago), licensed MIT. It adds 84 tokens to every session and 1,172 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.