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 gonta223/cc-books --skill skillgit clone --depth 1 https://github.com/gonta223/cc-booksWrote 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/gonta223/cc-books/skill)<a href="https://agentmods.dev/skills/gonta223/cc-books/skill"><img src="https://agentmods.dev/badge/skills/gonta223/cc-books/skill.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00029 | $0.01197 |
| Opus 5 | $0.00015 | $0.00598 |
| Sonnet 5 | $0.00006 | $0.00239 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade B, and why
daily-flipbook scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find ~/.claude/projects/ -name "*.jsonl" -newer /tmp/today_marker -not -path "*/subagents/*" 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily FlipBook Generator
今日のClaude Codeセッションログを読み取り、1日の振り返りをページめくりできる「本」として生成するスキル。
トリガー
/daily-flipbookで起動- 「今日の振り返り本作って」「日記本生成して」等
処理フロー
Step 1: セッションログの収集
今日のClaude Codeセッションログを両方のパスから収集する:
# パス1: デフォルト
~/.claude/projects/
# パス2: CLAUDE_CONFIG_DIR指定
~/claude-data/projects/
必ず両方のパスを検索すること。片方だけで「見つからない」は禁止。
ログファイルはJSONL形式。以下のコマンドで今日のセッションを見つける:
# 今日更新されたJSONLファイルを検索
find ~/.claude/projects/ -name "*.jsonl" -newer /tmp/today_marker -not -path "*/subagents/*" 2>/dev/null
find ~/claude-data/projects/ -name "*.jsonl" -newer /tmp/today_marker -not -path "*/subagents/*" 2>/dev/null
日付マーカーの作成:
touch -t $(date +%Y%m%d)0000 /tmp/today_marker
Step 2: ログの解析
各JSONLファイルから以下を抽出:
- ユーザーのメッセージ (
type: "user") → 何を依頼したか - アシスタントの応答 (
type: "assistant") → 何を実行したか - ツール使用 (
tool_use) → Write, Edit, Bash等の実行内容
これらを時系列で整理し、以下の構造にまとめる:
- セッション1: [プロジェクト名]
- やったこと: [概要]
- 成果物: [ファイル、コミット等]
- 学び: [気づき、発見]
- セッション2: ...
Step 3: 本の構成を決定
収集した情報から本の構成を自動生成:
| ページ | 内容 |
|---|---|
| 表紙 | 日付 + タイトル（「YYYY年MM月DD日の記録」） |
| はじめに | 今日のサマリー（セッション数、主な成果） |
| 各章 | セッションごとの詳細（やったこと、コード、学び） |
| 最終ページ | 今日の振り返り + 明日へのアクション |
構成ルール:
- 1セッションにつき1見開き（2ページ）
- 最大6章（12ページ）まで。それ以上は重要度で選別
- コードブロック、引用、ティップスボックスを適宜使用
Step 4: FlipBook HTMLを生成
テンプレート（index.html）をベースに、pages 配列を差し替えたHTMLを生成する。
出力先: /tmp/claude/daily-flipbook/YYYY-MM-DD.html
使用可能なCSSクラス:
.page-title— 大見出し.chapter-label— 章番号.page-body— 本文.code-block— コード（.comment,.keyword,.string,.propertyでハイライト）.quote— 引用ブロック.tip-box— ティップス（.tip-title+<ul>）.comparison— 2カラム比較（.col.good/.col.bad）.divider— 装飾区切り線.dropcap— ドロップキャップ（<p class="dropcap">）
Step 5: ブラウザで開く
open /tmp/claude/daily-flipbook/YYYY-MM-DD.html
出力例
表紙:
2026年4月5日の記録
── Today I Learned ──
章の例:
第一章: FlipBook UIを作った
「本のページめくるUI作れる？」から始まって、
CSS 3D transformsとWeb Audio APIで
ドラッグでめくれる本のUIを作った。
途中で「マウスで本当にめくれるように」と
要件が追加されて、ドラッグ操作の実装に。
mousedown → mousemove → mouseup で
角度を計算して、50度超えたら完了、
それ以下ならバネで戻す。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 131 lines · 29 tokens per session scan B 77362c415b42
daily-flipbook is a skill published in the GitHub repository gonta223/cc-books (57 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 1,197 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.
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.