Quick Start
Get up and running with awa in just a few minutes.
Install
Section titled “Install”bash npm install -g @ncoderz/awa bash npx @ncoderz/awa init Generate Agent Configuration Files
Section titled “Generate Agent Configuration Files”awa’s core value: one command generates AI agent configuration files for every tool your team uses — GitHub Copilot, Claude, Cursor, Gemini, and more — from a single template.
-
Navigate to your project
Terminal window cd my-project -
Generate files using the default awa template
Terminal window awa initThis generates agent configuration files into the current directory using awa’s bundled default template.
-
Generate with specific AI tool features
Terminal window awa init --features copilot claude cursorFeature flags control which sections are included. Enable only what you need.
-
Preview before writing (dry run)
Terminal window awa init --dry-run -
Discover available features
Terminal window awa template featuresLists all feature flags available in the template.
-
Check for drift after a template update
Terminal window awa template diff .See what would change in your project if you re-generated from the latest template.
Common Usage Patterns
Section titled “Common Usage Patterns”Using a Preset
Section titled “Using a Preset”# Enable all supported AI toolsawa init --preset full
# Enable a subsetawa init --preset full --remove-features roo agyUsing a Custom Template
Section titled “Using a Custom Template”# From a local directoryawa init --template ./my-templates
# From a GitHub repositoryawa init --template owner/repo
# From a specific branch or tagawa init --template owner/repo#v1.0.0Using a Config File
Section titled “Using a Config File”Create .awa.toml in your project root:
output = ".github/agents"template = "owner/repo"features = ["copilot", "claude"]Then simply run:
awa initWhat Gets Generated
Section titled “What Gets Generated”By default, awa generates files into the project root (configurable). These typically include:
- Agent instruction files (e.g.,
CLAUDE.md,AGENTS.md) - Prompt files in
.github/prompts/ - Workflow skills in
.github/skills/
The exact output depends on your template and feature flags.
Traceability and the awa Workflow
Section titled “Traceability and the awa Workflow”awa check and awa trace are separate from template generation — they are used when following the awa structured workflow for spec-driven development.
awa check— validates that traceability markers in your code reference real spec IDs, and flags uncovered acceptance criteria. Run this as part of your structured development workflow, not as part of template setup.awa trace <ID>— assembles the full trace for a requirement or component: spec text, implementation, and tests in one view. Useful when working on a feature or investigating coverage.
# Check traceability coverage across your codebaseawa check
# Trace a specific requirement or componentawa trace FEAT-1These commands require spec files (.awa/specs/) to be present. See the Workflow Guide for how to set up the full awa development workflow.
Spec Management Commands
Section titled “Spec Management Commands”Once you’re using the awa workflow, additional commands help manage your specifications:
# List all feature codes in your projectawa spec codes
# Renumber IDs to close gaps (e.g. after deleting requirements)awa spec renumber DIFF
# Recode a feature code to a new nameawa spec recode OLD NEW
# Merge two feature codes into oneawa spec merge SRC TGTSee the CLI Reference for full details on all spec management commands.
Next Steps
Section titled “Next Steps”- Workflow Guide — understand the awa workflow stages and traceability
- Traceability — how IDs and markers connect everything
- CLI Reference — all commands and options
- Template Engine — write your own templates
- Template Testing — verify templates with fixtures and snapshots
- Configuration —
.awa.tomlreference