Aider Universal Configuration

A comprehensive Aider configuration optimized for professional software engineering workflows with multi-model support, architect mode, and intelligent defaults.

What This Configuration Does

This skill provides a production-ready `.aider.conf.yaml` configuration that:

Instructions

When a user requests this Aider configuration:

1. **Create the configuration file** at `.aider.conf.yaml` in the user's working directory (or `~/.aider.conf.yaml` for global config)

2. **Use this exact configuration content**:

```yaml

openai-api-base: http://localhost:8080/v1

openai-api-base: https://glhf.chat/api/openai/v1

openai-api-base: https://api.kluster.ai/v1

openai-api-base: https://api.hyperbolic.xyz/v1

api-key:

#- openai=

#- openai=

#- openai=

- openai=

- anthropic=

- gemini=

- deepseek=

- codestral=

- mistral=

- github=

- cohere=

- xai=

- groq=

- together=

- openrouter=

architect: true

model: deepseek/deepseek-reasoner

model: o3-mini

model: o1

model: anthropic/claude-3-7-sonnet-20250219

model: gemini/gemini-2.0-pro-exp-02-05

model: gemini/gemini-2.0-flash-thinking-exp-01-21

edit-format: diff

editor-model: deepseek/deepseek-chat

editor-model: anthropic/claude-3-7-sonnet-20250219

editor-model: gpt-4o

editor-model: gemini/gemini-2.0-flash

editor-model: gemini/gemini-2.0-flash-lite

editor-model: codestral/codestral-latest

editor-model: mistral/mistral-large-latest

editor-edit-format: editor-diff

weak-model: codestral/codestral-latest

weak-model: gpt-4o-mini

weak-model: mistral/mistral-large-latest

weak-model: mistral/pixtral-large-latest

read:

- SYSTEM_PROMPT_PROGRAMMING.xml

- PRELIMINARY_DESIGN.md

yes-always: true

auto-commits: true

attribute-author: false

attribute-committer: false

show-diffs: false

test-cmd: go test ./... -v -race -cover -timeout 10s

auto-test: true

map-tokens: 2048

map-multiplier-no-files: 4

subtree-only: true

timeout: 301

cache-prompts: true

cache-keepalive-pings: 300

verbose: false

pretty: true

vim: true

editor: vim

multiline: true

detect-urls: false

code-theme: coffee

```

3. **Explain key configuration sections**:

- **API Keys**: Placeholders for multiple providers (user must fill in actual keys)

- **Architect Mode**: `architect: true` enables complex multi-file refactoring

- **Model Selection**:

- Main model: `o3-mini` (or alternatives commented out)

- Editor model: `claude-3-7-sonnet-20250219` for code editing

- Weak model: `codestral/codestral-latest` for lightweight tasks

- **Auto-commits**: Enabled with attribution control

- **Performance**: Cache enabled, 2048 map tokens, 301s timeout

- **Developer UX**: Vim mode, pretty output, multiline support

4. **Provide setup instructions**:

- User must replace `api-key` placeholder values with actual API keys

- Uncomment and modify `openai-api-base` if using alternative providers

- Uncomment `test-cmd` and `auto-test` for test-driven development

- Uncomment `read` files to include project-specific context

5. **Usage examples**:

```bash

# Use with default configuration

aider

# Override model for specific session

aider --model gpt-4o

# Disable auto-commits for this session

aider --no-auto-commits

# Use architect mode with specific files

aider --architect src/main.py tests/test_main.py

```

Configuration Highlights

Constraints

Notes