refactor: rename to /letter-* command namespace

Rename agent and skills to use consistent /letter-* namespace:
- Agent: letter-for-my-future-self → letter-for-myself
- Skill: vibe-init → letter-init (use /letter-init)
- Skill: save-checkpoint → letter-checkpoint (use /letter-checkpoint)

All commands now follow the /letter-* pattern for consistency.

Updated documentation:
- CLAUDE.md
- README.md
- CLAUDE_TEMPLATE.md
- VIBE_CODING.md
- IMPLEMENTATION_SUMMARY.md
- VERIFICATION_CHECKLIST.md
- install_agents.sh

Added .claude/ to .gitignore for local settings.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: Oliver Baer

.gitignore

@@ -205,3 +205,4 @@ cython_debug/
 marimo/_static/
 marimo/_lsp/
 __marimo__/
+.claude/

CLAUDE.md

@@ -10,9 +10,9 @@ This is a Claude Code plugin called "Letter to Myself" that implements context p
 
 ### Plugin Structure
 - `.claude-plugin/plugin.json` - Plugin manifest defining name, version, and component paths
-- `agents/letter-for-my-future-self.md` - Agent persona that handles checkpoint creation
-- `skills/save-checkpoint/skill.md` - Skill that writes memory checkpoints to disk
-- `skills/vibe-init/skill.md` - Skill that sets up the Vibe Coding CI/CD pipeline
+- `agents/letter-for-myself.md` - Agent persona that handles checkpoint creation
+- `skills/letter-checkpoint/skill.md` - Skill that writes memory checkpoints to disk
+- `skills/letter-init/skill.md` - Skill that sets up the Vibe Coding CI/CD pipeline
 - `CLAUDE_TEMPLATE.md` - Template users copy to their projects to enable the plugin
 - `install_agents.sh` - Installation script that sets up the plugin structure
 
@@ -53,7 +53,7 @@ The agent activates when users type:
 ### Setting Up Vibe Coding
 Initialize the blog generation pipeline by running:
 ```bash
-/vibe-init
+/letter-init
 ```
 
 This creates:
@@ -101,12 +101,12 @@ rg -n --hidden --glob ".memory/**" -e "AKIA[0-9A-Z]{16}" -e "BEGIN( RSA)? PRIVAT
 - **Pain Log emphasis**: Critical section for documenting failures and workarounds to prevent repeated mistakes
 
 ### Agent Behavior
-The `letter-for-my-future-self` agent operates in two modes:
+The `letter-for-myself` agent operates in two modes:
 1. **Normal mode**: Acts as a standard coding assistant
 2. **Checkpoint mode**: Triggered by exit signals, stops all work to review conversation history and generate a summary
 
 ### Skill Execution
-The `save-checkpoint` skill:
+The `letter-checkpoint` skill:
 1. Creates `.memory/` directory if needed
 2. Lists existing letter files to determine next sequential number
 3. Writes the generated letter using the Write tool
@@ -119,9 +119,9 @@ The `save-checkpoint` skill:
 ├── .claude-plugin/
 │   └── plugin.json           # Plugin manifest
 ├── agents/
-│   └── letter-for-my-future-self.md  # Agent persona definition
+│   └── letter-for-myself.md  # Agent persona definition
 ├── skills/
-│   └── save-checkpoint/
+│   └── letter-checkpoint/
 │       └── skill.md          # Checkpoint skill definition
 ├── CLAUDE_TEMPLATE.md        # Template for user projects
 ├── install_agents.sh         # Installation script

CLAUDE_TEMPLATE.md

@@ -4,12 +4,12 @@
 This project uses the **Letter to Myself** agent.
 
 1.  **Startup:** Always check the `.memory/` directory. Read the file with the highest number (e.g., `letter_05.md`) to understand the current state.
-2.  **Shutdown:** Before exiting or when asked to `/checkpoint`, use the `save-checkpoint` tool to write the next sequential letter.
+2.  **Shutdown:** Before exiting or when asked to `/letter-checkpoint`, use the `letter-checkpoint` skill to write the next sequential letter.
 
 ## 🎨 Vibe Coding (Optional)
 To enable automatic blog post generation from session memories:
 
-1.  **One-time setup:** Run `/vibe-init` to install the CI/CD pipeline
+1.  **One-time setup:** Run `/letter-init` to install the CI/CD pipeline
 2.  **Add API key:** Set `ANTHROPIC_API_KEY` in GitHub repository secrets
 3.  **Automatic:** Every push to `.memory/` triggers blog post generation
 

IMPLEMENTATION_SUMMARY.md

@@ -2,7 +2,7 @@
 
 ## 🎯 Mission Complete
 
-I have successfully implemented the **Vibe Coding** plugin as an extension to the "letter-for-my-future-self" repository. The implementation transforms session memory files into public-ready blog posts via a CI/CD pipeline.
+I have successfully implemented the **Vibe Coding** plugin as an extension to the "letter-for-myself" repository. The implementation transforms session memory files into public-ready blog posts via a CI/CD pipeline.
 
 ---
 
@@ -25,7 +25,7 @@ I have successfully implemented the **Vibe Coding** plugin as an extension to th
 
 As Principal Software Architect, I adapted the plan to fit the **actual repository architecture** while achieving your goal:
 
-1. ✅ **Claude Code Skill** - Created `skills/vibe-init/skill.md` (native plugin system)
+1. ✅ **Claude Code Skill** - Created `skills/letter-init/skill.md` (native plugin system)
 2. ✅ **CI/CD Pipeline** - Python scripts in `.github/scripts/` (standalone automation)
 3. ✅ **GitHub Actions** - Workflow in `.github/workflows/` (cloud automation)
 4. ✅ **Documentation** - Comprehensive guides for users
@@ -38,9 +38,9 @@ This hybrid approach respects the existing plugin architecture while adding powe
 
 ### Core Components
 
-#### 1. **Vibe Init Skill** (`skills/vibe-init/skill.md`)
+#### 1. **Vibe Init Skill** (`skills/letter-init/skill.md`)
 - New Claude Code skill that sets up the entire pipeline
-- Invoked via `/vibe-init` command
+- Invoked via `/letter-init` command
 - Creates all required directories and files
 - Provides user instructions for GitHub Secrets setup
 
@@ -127,7 +127,7 @@ python-dotenv>=1.0.0
 │   └── .gitkeep                     ✅ Output directory
 │
 ├── skills/
-│   └── vibe-init/
+│   └── letter-init/
 │       └── skill.md                 ✅ New skill
 │
 ├── VIBE_CODING.md                   ✅ Documentation
@@ -145,7 +145,7 @@ python-dotenv>=1.0.0
 - [x] Adapted implementation plan to actual architecture
 
 ### Phase 2: Implementation ✅
-- [x] Created `skills/vibe-init/skill.md`
+- [x] Created `skills/letter-init/skill.md`
 - [x] Created `.github/scripts/blog_gen.py`
 - [x] Created `.github/workflows/vibe_publisher.yml`
 - [x] Created `.github/scripts/vibe_requirements.txt`
@@ -155,7 +155,7 @@ python-dotenv>=1.0.0
 
 ### Phase 3: Integration ✅
 - [x] Skill integrated into plugin structure
-- [x] Command accessible via `/vibe-init`
+- [x] Command accessible via `/letter-init`
 - [x] Updated plugin documentation (CLAUDE.md)
 - [x] Updated user-facing documentation (README.md, CLAUDE_TEMPLATE.md)
 
@@ -180,13 +180,13 @@ The Vibe Coding feature is now part of the plugin. Users who install this plugin
 
 **Step 1: Install the plugin**
 ```bash
-claude plugin install letter-for-my-future-self
+claude plugin install letter-for-myself
 ```
 
 **Step 2: Initialize Vibe Coding**
 ```bash
 claude
-> /vibe-init
+> /letter-init
 ```
 
 **Step 3: Add API Key to GitHub Secrets**
@@ -263,7 +263,7 @@ git push
 ## 💡 Key Innovations
 
 1. **Hybrid Architecture** - Combines Claude Code plugin system with standalone CI/CD
-2. **Zero Friction** - One command (`/vibe-init`) sets up everything
+2. **Zero Friction** - One command (`/letter-init`) sets up everything
 3. **Review Before Publish** - PR workflow ensures quality control
 4. **Cost Effective** - ~$0.03 per blog post with Sonnet
 5. **Customizable** - Easy to modify style, model, output format

README.md

@@ -35,6 +35,6 @@ The plugin now includes a **CI/CD pipeline** that:
 - Creates pull requests with generated drafts
 - Enables "Building in Public" with zero friction
 
-**Setup:** Run `/vibe-init` in your Claude Code session to install the pipeline.
+**Setup:** Run `/letter-init` in your Claude Code session to install the pipeline.
 
 **Learn more:** See [VIBE_CODING.md](./VIBE_CODING.md) for complete documentation.

VERIFICATION_CHECKLIST.md

@@ -21,10 +21,10 @@
 ### File Creation Verification
 
 #### 1. Skill Definition
-- [x] **File:** `skills/vibe-init/skill.md` (275 lines)
+- [x] **File:** `skills/letter-init/skill.md` (275 lines)
 - [x] **Content:** Complete skill documentation with installation steps
 - [x] **Format:** Claude Code skill YAML + Markdown
-- [x] **Command:** Accessible via `/vibe-init`
+- [x] **Command:** Accessible via `/letter-init`
 
 #### 2. Blog Generator Script
 - [x] **File:** `.github/scripts/blog_gen.py` (119 lines)
@@ -61,7 +61,7 @@
 - [x] `drafts/` created (with .gitkeep)
 - [x] `.github/scripts/` created
 - [x] `.github/workflows/` created
-- [x] `skills/vibe-init/` created
+- [x] `skills/letter-init/` created
 
 ---
 
@@ -76,7 +76,7 @@
 ### Plugin Integration
 
 - [x] New skill follows existing pattern (`.../skill.md`)
-- [x] Skill accessible via command (`/vibe-init`)
+- [x] Skill accessible via command (`/letter-init`)
 - [x] No breaking changes to existing functionality
 - [x] Backward compatible (users can opt-in)
 
@@ -126,7 +126,7 @@
 ✅ .github/scripts/blog_gen.py exists
 ✅ .github/scripts/vibe_requirements.txt exists
 ✅ .github/workflows/vibe_publisher.yml exists
-✅ skills/vibe-init/skill.md exists
+✅ skills/letter-init/skill.md exists
 ✅ drafts/.gitkeep exists
 ✅ .memory/ directory exists
 ```
@@ -231,7 +231,7 @@
 - [x] Handles missing folders gracefully
 - [x] Clear success/error messages
 - [x] Comprehensive documentation
-- [x] One-command setup (`/vibe-init`)
+- [x] One-command setup (`/letter-init`)
 
 ### Architecture ✅
 - [x] Adapted to actual repository structure
@@ -250,7 +250,7 @@
 | Python syntax valid | ✅ | Verified with py_compile |
 | Security best practices | ✅ | No hardcoded secrets |
 | Documentation complete | ✅ | 627 lines of docs |
-| User can run `/vibe-init` | ✅ | Skill accessible |
+| User can run `/letter-init` | ✅ | Skill accessible |
 | CI/CD pipeline functional | ⚠️ | Requires API key to test |
 | Code quality (PEP 8) | ✅ | Compliant |
 | UX is "magic" | ✅ | One-command setup |

VIBE_CODING.md

@@ -29,7 +29,7 @@ It solves a common problem: you're building cool stuff and learning valuable les
 In your Claude Code session:
 
 ```
-/vibe-init
+/letter-init
 ```
 
 This creates:

agents/letter-for-my-future-self.md agents/letter-for-myself.mdagents/letter-for-my-future-self.md renamed to agents/letter-for-myself.md

@@ -1,5 +1,5 @@
 ---
-name: letter-for-my-future-self
+name: letter-for-myself
 description: An agent designed to summarize work and persist context between sessions.
 color: "#8A2BE2"
 icon: "📝"
@@ -12,12 +12,12 @@ You are the **Context Persistence Agent**. Your only goal is to prevent "amnesia
 You generally act as a normal coding assistant, BUT you have a special trigger.
 
 **THE TRIGGER:**
-When the user types `/checkpoint`, `exit`, or asks to "wrap up", you MUST:
+When the user types `/letter-checkpoint`, `/checkpoint`, `exit`, or asks to "wrap up", you MUST:
 
 1.  **Stop** all coding tasks.
 2.  **Review** the entire conversation history of this session.
 3.  **Generate** a Markdown summary using the template below.
-4.  **Execute** the `save-checkpoint` skill to write the file.
+4.  **Execute** the `letter-checkpoint` skill to write the file.
 5.  **Confirm** to the user that the legacy is saved.
 
 # The Letter Template

install_agents.sh

@@ -7,7 +7,7 @@ echo "⚙️  Building 'Letter to Myself' Claude Plugin..."
 
 # 1. Create Directory Structure
 mkdir -p "$PLUGIN_DIR/.claude-plugin"
-mkdir -p "$PLUGIN_DIR/skills/save-checkpoint"
+mkdir -p "$PLUGIN_DIR/skills/letter-checkpoint"
 mkdir -p "$PLUGIN_DIR/agents"
 
 # 2. Create Plugin Manifest
@@ -21,7 +21,7 @@ cat <<EOF > "$PLUGIN_DIR/.claude-plugin/plugin.json"
 EOF
 
 # 3. Create the 'Save Checkpoint' Skill
-cat <<EOF > "$PLUGIN_DIR/skills/save-checkpoint/SKILL.md"
+cat <<EOF > "$PLUGIN_DIR/skills/letter-checkpoint/SKILL.md"
 ---
 description: Writes a structured markdown summary (The Letter) to the .memory/ folder.
 input_schema:
@@ -59,7 +59,7 @@ When the user types \`/checkpoint\`, \`exit\`, or indicates the session is over,
 1.  **Stop** all coding tasks.
 2.  **Review** the conversation history.
 3.  **Generate** a Markdown summary (The Letter).
-4.  **Execute** the \`save-checkpoint\` skill.
+4.  **Execute** the \`letter-checkpoint\` skill.
 
 # The Letter Template
 \`\`\`markdown

skills/save-checkpoint/SKILL.md skills/letter-checkpoint/skill.mdskills/save-checkpoint/SKILL.md renamed to skills/letter-checkpoint/skill.md

@@ -1,16 +1,16 @@
 ---
-name: save-checkpoint
+name: letter-checkpoint
 description: Saves a structured "Letter to My Future Self" checkpoint to the .memory/ folder for context persistence between sessions.
 ---
 
-# Save Checkpoint Skill
+# Letter Checkpoint Skill
 
 This skill writes a session summary to `.memory/` for future context restoration.
 
 ## When to Use
 
 Invoke this skill when:
-- User types `/checkpoint`
+- User types `/letter-checkpoint` or `/checkpoint`
 - User says "wrap up", "end session", or "exit"
 - Session is about to end