Complete Aider AI pair programming assistant configuration with all available settings for model selection, git integration, output formatting, and workflow automation.
This skill has safety concerns that you should review before use. Some patterns were detected that may pose a risk.Safety score: 60/100.
KillerSkills scans all public content for safety. Use caution before installing or executing flagged content.
Complete configuration guide for Aider, the AI pair programming assistant that works with your terminal and git repository.
This skill provides comprehensive configuration for Aider, covering all available settings including API keys, model selection, git integration, output formatting, testing/linting automation, and workflow customization.
Aider reads configuration from `.aider.conf.yaml` placed in:
```yaml
openai-api-key: YOUR_OPENAI_KEY
anthropic-api-key: YOUR_ANTHROPIC_KEY
model: claude-3-5-sonnet-20240620 # Specify any model
opus: true # Use Claude 3 Opus
sonnet: true # Use Claude 3.5 Sonnet
4o: true # Use GPT-4o
4-turbo: true # Use GPT-4 Turbo
35turbo: true # Use GPT-3.5 Turbo
weak-model: gpt-3.5-turbo
```
```yaml
openai-api-base: https://custom-api.example.com
openai-api-type: azure
openai-api-version: 2023-05-15
openai-api-deployment-id: your-deployment
openai-organization-id: org-xxx
edit-format: diff # or 'whole', 'udiff'
map-tokens: 1024 # Tokens for repo map (0 to disable)
max-chat-history-tokens: 4096
verify-ssl: true
show-model-warnings: true
model-settings-file: .aider.model.settings.yml
model-metadata-file: .aider.model.metadata.json
```
```yaml
git: true # Enable git integration
gitignore: true # Add .aider* to .gitignore
aiderignore: .aiderignore # Aider ignore file
auto-commits: true # Auto-commit LLM changes
dirty-commits: true # Allow commits when repo is dirty
attribute-author: true # Attribute in git author name
attribute-committer: true # Attribute in committer name
attribute-commit-message: false # Prefix commits with 'aider:'
dry-run: false # Test without modifying files
show-diffs: true # Show diffs when committing
```
```yaml
dark-mode: true # Colors for dark terminal
light-mode: false # Colors for light terminal
pretty: true # Enable colorized output
stream: true # Enable streaming responses
user-input-color: "#00cc00"
tool-output-color: "#888888"
tool-error-color: "#FF2222"
assistant-output-color: "#0088ff"
code-theme: monokai # Options: default, monokai, solarized-dark, solarized-light
```
```yaml
auto-lint: true
lint: false # Run lint on startup
lint-cmd:
- "python: flake8 --select=E,W,F"
- "javascript: eslint --fix"
- "typescript: eslint --fix"
auto-test: false
test: false # Run tests on startup
test-cmd: pytest tests/
```
```yaml
input-history-file: .aider.input.history
chat-history-file: .aider.chat.history.md
restore-chat-history: false
llm-history-file: .aider.llm.history # Log all LLM interactions
```
```yaml
vim: false # Use VI editing mode
yes: false # Auto-confirm all prompts
message: "Fix the bug in auth.py" # Single message mode
message-file: prompt.txt # Message from file
commit: false # Commit and exit
gui: false # Run in browser
verbose: false
show-repo-map: false # Print repo map and exit
show-prompts: false # Print system prompts and exit
check-update: false
skip-check-update: false
```
```yaml
anthropic-api-key: ${ANTHROPIC_API_KEY}
model: claude-3-5-sonnet-20240620
auto-commits: true
auto-lint: true
dark-mode: true
restore-chat-history: true
```
Then run: `aider file1.py file2.js`
```yaml
message-file: fix-request.txt
auto-commits: true
auto-test: true
test-cmd: npm test
yes: true # Non-interactive mode
```
```yaml
dry-run: true # Don't modify files
show-diffs: true
auto-commits: false
verbose: true
```
```yaml
openai-api-base: https://api.groq.com/openai/v1
model: mixtral-8x7b-32768
weak-model: mixtral-8x7b-32768
show-model-warnings: false
```
You can use environment variables in your config:
```yaml
anthropic-api-key: ${ANTHROPIC_API_KEY}
openai-api-key: ${OPENAI_API_KEY}
env-file: .env.local # Custom env file location
```
All config options can be overridden via CLI:
```bash
aider --model gpt-4o --auto-test --test-cmd "npm test"
aider --dark-mode --vim --restore-chat-history
aider --message "Add error handling" file.py
```
1. **Security**: Store API keys in environment variables, not directly in config
2. **Team Sharing**: Commit `.aider.conf.yaml` to your repo for consistent team settings (without secrets)
3. **Personal Overrides**: Use `~/.aider.conf.yaml` for personal preferences
4. **Model Selection**: Use `sonnet` for complex tasks, `weak-model` for summaries/commits
5. **Testing**: Enable `auto-test` only for projects with fast test suites
6. **History**: Enable `restore-chat-history` for continued context across sessions
7. **Git Safety**: Keep `auto-commits: true` but review changes regularly
```bash
aider --help # Show all options
aider --models sonnet # List available models matching 'sonnet'
aider --show-prompts # View system prompts
aider --version # Show version
aider --config custom.yml # Use custom config file
```
Leave a review
No reviews yet. Be the first to review this skill!
# Download SKILL.md from killerskills.ai/api/skills/aider-configuration-lgdl8u/raw