[2.11.1] Remove /prime command from plugin

Fixes #41

The /prime command was a personal setup command that shouldn't have been
included in the distributed plugin. It caused confusion when users had
hooks that auto-invoked it on session start.

Users who want a prime command can add it to their personal ~/.claude/commands/

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Kieran Klaassen
2025-12-10 19:02:24 -08:00
parent 2a8f19936a
commit f0a49f5b18
4 changed files with 3 additions and 98 deletions

View File

@@ -1,7 +1,7 @@
{
"name": "compound-engineering",
"version": "2.11.0",
"description": "AI-powered development tools. 25 agents, 19 commands, 12 skills, 2 MCP servers for code review, research, design, and workflow automation.",
"description": "AI-powered development tools. 25 agents, 17 commands, 12 skills, 2 MCP servers for code review, research, design, and workflow automation.",
"author": {
"name": "Kieran Klaassen",
"email": "kieran@every.to",

View File

@@ -26,6 +26,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Removed
- **`prime.md`** - Removed from plugin (personal setup command, not for distribution)
- **`codify.md`** - Removed deprecated command (replaced by `/compound`)
## [2.10.0] - 2025-12-10

View File

@@ -7,7 +7,7 @@ AI-powered development tools that get smarter with every use. Make each unit of
| Component | Count |
|-----------|-------|
| Agents | 25 |
| Commands | 19 |
| Commands | 17 |
| Skills | 12 |
| MCP Servers | 2 |
@@ -87,7 +87,6 @@ Core workflow commands use `workflows:` prefix to avoid collisions with built-in
| `/generate_command` | Generate new slash commands |
| `/heal-skill` | Fix skill documentation issues |
| `/plan_review` | Multi-agent plan review in parallel |
| `/prime` | Prime/setup command |
| `/report-bug` | Report a bug in the plugin |
| `/reproduce-bug` | Reproduce bugs using logs and console |
| `/resolve_parallel` | Resolve TODO comments in parallel |

View File

@@ -1,95 +0,0 @@
---
name: prime
description: Prime Claude with project context by reading key files and understanding the codebase structure
argument-hint: [optional: specific area to focus on]
---
# Prime Command
Prime yourself with essential project context to work effectively in this codebase.
## Workflow
### 1. Discover Project Structure
<task>
First, understand the project layout:
```bash
# Find project root indicators
ls -la | head -20
# Check for common config files
ls -la *.json *.yml *.yaml *.toml 2>/dev/null | head -10
# Find source directories
ls -d */ 2>/dev/null | head -10
```
</task>
### 2. Read Key Documentation
<task>
Read project documentation in this order:
1. **CLAUDE.md** (if exists) - Project-specific Claude instructions
2. **README.md** - Project overview and setup
3. **CONTRIBUTING.md** (if exists) - Development guidelines
4. **.claude/** directory (if exists) - Custom commands and config
</task>
### 3. Understand Tech Stack
<task>
Identify the technology stack:
- **Ruby/Rails**: Look for `Gemfile`, `config/routes.rb`
- **JavaScript/Node**: Look for `package.json`, `tsconfig.json`
- **Python**: Look for `requirements.txt`, `pyproject.toml`, `setup.py`
- **Go**: Look for `go.mod`
- **Rust**: Look for `Cargo.toml`
</task>
### 4. Map Key Directories
<task>
For the identified stack, explore the structure:
**Rails projects:**
- `app/models/` - Domain models
- `app/controllers/` - Request handlers
- `app/views/` or `app/components/` - UI layer
- `config/` - Configuration
- `db/schema.rb` - Database structure
**Node/JS projects:**
- `src/` or `lib/` - Source code
- `components/` - UI components
- `api/` or `routes/` - API endpoints
- `tests/` or `__tests__/` - Test files
</task>
### 5. Summarize Context
<output>
After priming, provide a brief summary:
## Project Context
**Name:** [project name]
**Stack:** [technologies identified]
**Key directories:** [important paths]
**Special instructions:** [from CLAUDE.md if present]
Ready to help with: [list 3-5 things you can now assist with]
</output>
## Focus Areas
If the user specified a focus area ($ARGUMENTS), prioritize:
- **"models"** - Focus on data layer and business logic
- **"api"** - Focus on endpoints and request handling
- **"frontend"** - Focus on UI components and views
- **"tests"** - Focus on test structure and patterns
- **"config"** - Focus on configuration and environment