agentleFS
ShawnBaekShawnBaek/kindle-weekly-letter/CLAUDE.md

kindle-weekly-letter

CLAUDE.md2 starsChanged 8 months agoMITView on GitHub

Automated weekly Kindle newsletter — AI research agents collect articles daily, compile into a readable EPUB book, and deliver to your Kindle every Sunday.

  • Reads credentials
  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. Synsemantic-genuslamna112/kindle-weekly-letter★ 1100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this CLAUDE.md into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After running /setup-kindle, two launchd agents are created:

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Kindle Weekly Letter

Automated weekly Kindle newsletter — AI research agents collect articles daily, compile into a readable EPUB book, and deliver to your Kindle every Sunday.

Quick Start

/setup-kindle          # Configure email, Kindle, and scheduling
/collect-now           # Start collecting articles immediately
/compile-now           # Compile and send EPUB now
/add-topic React       # Add a custom topic
/sources list          # View all sources with votes
/sources vote ios "Hacking with Swift"   # Upvote a source

Default Topics (6)

  1. English for Software Engineers
  2. AI Engineering News (CTO-level)
  3. iOS Engineering
  4. Travel App Business
  5. Singapore & Korea News (official publishers only)
  6. C++ / C / Rust / Python

Architecture

  • Daily collection: 6 Agent subagents research topics in parallel, accumulate articles in output/weekly/
  • Sunday compilation: Compile all articles, get user approval, generate EPUB, send to Kindle
  • Each topic targets 10 articles/week — agents stop when a topic hits 10
  • Sources: sources.json — community-curated, votable source list per topic
  • Skills: .claude/skills/ — slash commands for setup, topics, sources, manual triggers

File Structure

├── .claude/skills/          # Slash commands (/setup-kindle, /add-topic, etc.)
├── .claude-plugin/          # Plugin manifest for distribution
├── prompts/                 # Agent prompts (read sources.json for source priorities)
│   ├── daily_collector.md   # Daily collection orchestrator
│   ├── sunday_compiler.md   # Sunday EPUB compilation orchestrator
│   └── agent_*.md           # Per-topic research agents
├── src/
│   ├── epub_builder.py      # EPUB generation (ebooklib + jinja2)
│   ├── email_sender.py      # SMTP email sender
│   ├── article_store.py     # Daily article accumulator with dedup
│   ├── content_formatter.py # HTML sanitization for Kindle
│   └── config.py            # Topic definitions, email config
├── sources.json             # Votable source list per topic
├── templates/               # EPUB Jinja2 templates
├── styles/kindle.css        # Kindle-optimized CSS
└── output/                  # Generated EPUBs and weekly article store

Scheduling (launchd — macOS)

After running /setup-kindle, two launchd agents are created:

  • com.kindle-letter.daily-collector — Daily at configured time
  • com.kindle-letter.sunday-compiler — Sunday at configured time

Key Commands

# Install dependencies
uv venv && source .venv/bin/activate && uv pip install -e .

# Build EPUB manually
python3 -m src.epub_builder --input output/content.json --output output/newsletter.epub

# Send EPUB manually
python3 -m src.email_sender --epub output/newsletter.epub

# Check collection status
python3 -c "from src.article_store import get_status_summary; print(get_status_summary())"

Environment Variables (.env)

  • EMAIL_ADDRESS — Your email address
  • EMAIL_APP_PASSWORD — App Password (not your regular password)
  • SMTP_HOST — Default: smtp.mail.yahoo.com
  • SMTP_PORT — Default: 465
  • KINDLE_EMAILS — Comma-separated Kindle email addresses

Plugin Installation (for other users)

/plugin marketplace add https://raw.githubusercontent.com/ShawnBaek/kindle-letter/main/marketplace.json
/plugin install kindle-letter

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.