config
Manage the user-level AIWG configuration file for persistent preferences across all projects
Best use case
config is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
It is a strong fit for teams already working in Codex.
Manage the user-level AIWG configuration file for persistent preferences across all projects
Teams using config should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/config/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How config Compares
| Feature / Agent | config | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Manage the user-level AIWG configuration file for persistent preferences across all projects
Which AI agents support this skill?
This skill is designed for Codex.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# Config You manage the user-level AIWG configuration file. This is the persistent preferences store that applies across all projects: default provider, default model, telemetry opt-in/out, and other global settings. ## Triggers Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description): - "what's my default provider" → get subcommand for `provider` - "turn off telemetry" → set subcommand for `telemetry` - "where is the aiwg config file" → path subcommand - "reset aiwg to defaults" → reset subcommand - "open config in my editor" → edit subcommand - "is my config valid" → validate subcommand ## Trigger Patterns Reference | Pattern | Example | Action | |---------|---------|--------| | List all settings | "show my aiwg config" | Run `aiwg config list` | | Read a value | "what's my default model?" | Run `aiwg config get defaultModel` | | Write a value | "set default provider to copilot" | Run `aiwg config set defaultProvider copilot` | | Validate | "check my config for errors" | Run `aiwg config validate` | | Reset | "reset config to defaults" | Run `aiwg config reset` | | Locate file | "where is the config file?" | Run `aiwg config path` | | Open editor | "edit config" | Run `aiwg config edit` | ## Behavior When triggered: 1. **Extract intent**: - Which subcommand: `list`, `get`, `set`, `validate`, `reset`, `path`, or `edit`? - For `get`/`set`: what is the key? For `set`: what is the new value? - Is a custom config directory specified via `--config-dir`? 2. **Resolve config directory** (in order): 1. `AIWG_CONFIG` environment variable 2. `--config-dir <path>` flag 3. `~/.aiwg/config.json` 4. `~/.config/aiwg/config.json` 3. **Run the appropriate command**: ```bash # Show all configuration values aiwg config list # Read a specific key aiwg config get <key> # Write a value aiwg config set <key> <value> # Validate the config file aiwg config validate # Reset to factory defaults aiwg config reset # Show resolved config file path aiwg config path # Open in $EDITOR aiwg config edit # Use a custom config directory aiwg config list --config-dir /path/to/config ``` 4. **Common configuration keys**: | Key | Type | Description | |-----|------|-------------| | `defaultProvider` | string | Active provider (e.g., `claude-code`, `copilot`) | | `defaultModel` | string | Model override (e.g., `claude-opus-4-5`) | | `telemetry` | boolean | Usage telemetry opt-in | | `updateChannel` | string | `stable`, `next`, or `nightly` | | `configDir` | string | Custom config directory path | 5. **Report results** — For `list`/`get`, display the value(s). For `set`, confirm what changed. For `validate`, show any errors found. For `reset`, warn the user that this is destructive and confirm before proceeding. ## Examples ### Example 1: Show all settings **User**: "Show me my AIWG configuration" **Extraction**: List all settings **Action**: ```bash aiwg config list ``` **Response**: Displays all keys and their current values, e.g.: ``` defaultProvider claude-code defaultModel (not set — using platform default) telemetry true updateChannel stable ``` --- ### Example 2: Change default provider **User**: "Set my default provider to GitHub Copilot" **Extraction**: Set `defaultProvider` to `copilot` **Action**: ```bash aiwg config set defaultProvider copilot ``` **Response**: "Set `defaultProvider` to `copilot`. This will be used as the default for `aiwg use` and `aiwg sync` going forward." --- ### Example 3: Disable telemetry **User**: "Turn off telemetry" **Extraction**: Set `telemetry` to `false` **Action**: ```bash aiwg config set telemetry false ``` **Response**: "Telemetry disabled. AIWG will no longer send usage data." --- ### Example 4: Locate config file **User**: "Where does AIWG store its config?" **Extraction**: Path lookup **Action**: ```bash aiwg config path ``` **Response**: "Config file: `~/.aiwg/config.json` (exists)" --- ### Example 5: Validate after manual edit **User**: "I edited the config manually — check if it's valid" **Extraction**: Validate request **Action**: ```bash aiwg config validate ``` **Response**: "Config valid. No errors found." — or lists specific schema errors if invalid. --- ### Example 6: Custom config directory **User**: "Check config using the team shared config dir at /opt/aiwg-team" **Extraction**: List with `--config-dir` **Action**: ```bash aiwg config list --config-dir /opt/aiwg-team ``` **Response**: Displays config values loaded from `/opt/aiwg-team/config.json`. ## Clarification Prompts If the user's intent is ambiguous: - "Which config key are you asking about? (run `aiwg config list` to see all keys)" - "What value should I set `<key>` to?" - "`aiwg config reset` will overwrite all settings with factory defaults. Proceed?" ## References - @$AIWG_ROOT/src/cli/handlers/subcommands.ts — Config command handler - @$AIWG_ROOT/docs/cli-reference.md — CLI reference
Related Skills
ralph-config
View and configure agent loop settings — show, set, reset, and apply named presets
config-validator
Validate AIWG configuration files and project setup for correctness and completeness
aiwg-orchestrate
Route structured artifact work to AIWG workflows via MCP with zero parent context cost
venv-manager
Create, manage, and validate Python virtual environments. Use for project isolation and dependency management.
pytest-runner
Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.
vitest-runner
Execute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.
eslint-checker
Run ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.
repo-analyzer
Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.
pr-reviewer
Review GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.
YouTube Acquisition
yt-dlp patterns for acquiring content from YouTube and video platforms
Quality Filtering
Accept/reject logic and quality scoring heuristics for media content
Provenance Tracking
W3C PROV-O patterns for tracking media derivation chains and production history