Help us improve
Share bugs, ideas, or general feedback.
npx claudepluginhub clearclown/claude-code-aida-red --plugin aidaHow this command is triggered — by the user, by Claude, or both
Slash command
/aida:initThe summary Claude sees in its command listing — used to decide when to auto-load this command
# AIDA Init Initialize the AIDA directory structure and configuration files for a new workspace. ## Usage - `project-dir`: Optional. Directory where project code will be generated (default: current directory) ## Execution Steps ### Step 1: Create Directory Structure ### Step 2: Initialize session.json Create `.aida/state/session.json`: ### Step 3: Initialize kanban.md Create `.aida/kanban.md`: ### Step 4: Output Confirmation ## Output Format ### Success ### Already Initialized ## Directory Structure After initialization:
/toolkit-initInitializes project with ai-toolkit structure (53 files), smartly detecting new setup or update/sync mode. Minimal questions for new projects; supports --force and --dry-run.
/conductor-setupInitializes Conductor environment in new projects by creating conductor/ directory, config.json, track registry, status docs, decision log, and knowledge files. Shows status if already exists.
/dev-setupInitializes Claude Code infrastructure in a project directory, creating AI skills, hooks, settings, MASTER_PLAN.md template, and CLAUDE.md guidance. Supports path and --minimal flag.
/initInitializes beads issue tracking database in current directory with optional prefix (defaults to dir name). Shows DB location, prefix, workflow overview, next steps; displays stats if already set up.
/initInitializes guided UI design for dashboards, apps, and tools. Assesses intent, proposes styles with rationale, builds components, and offers to save patterns.
/initSets up Repowise for the current codebase. Installs if needed, asks about indexing preferences (index-only or full with LLM), and runs the indexing process.
Share bugs, ideas, or general feedback.
Initialize the AIDA directory structure and configuration files for a new workspace.
/aida:init [project-dir]
project-dir: Optional. Directory where project code will be generated (default: current directory)# AIDA management directories (always in .aida/)
mkdir -p .aida/state
mkdir -p .aida/checkpoints
mkdir -p .aida/artifacts
mkdir -p .aida/sessions
mkdir -p .aida/tasks
mkdir -p .aida/results
mkdir -p .aida/specs
Create .aida/state/session.json:
{
"session_id": null,
"started_at": null,
"phase": "idle",
"status": "initialized",
"user_request": null,
"project_dir": ".",
"agents": {
"conductor": {"status": "waiting"},
"leaders": [],
"players": []
},
"phases": {
"1": {"status": "pending"},
"2": {"status": "pending"},
"3": {"status": "pending"},
"4": {"status": "pending"},
"5": {"status": "pending"}
},
"tasks": [],
"metrics": {
"tasks_completed": 0,
"tasks_failed": 0
}
}
Create .aida/kanban.md:
# AIDA Kanban Board
## Meta
**Session**: (not started)
**Phase**: idle
**Updated**: <TIMESTAMP>
## Backlog
(no tasks)
## In Progress
(none)
## Done
(none)
AIDA Workspace Initialized
Created:
.aida/
state/
session.json
checkpoints/
artifacts/
sessions/
tasks/
results/
specs/
kanban.md
Project code will be generated in: ./
Next step:
/aida:start "project description" to begin pipeline
AIDA workspace already initialized
Current state:
- Session: <session_id or "none">
- Phase: <phase>
- Project dir: <project_dir>
Options:
1. Continue current session: /aida:work
2. Check status: /aida:status
3. Start new pipeline: /aida:start "description"
After initialization:
.aida/ # AIDA management (specs, state, artifacts)
state/
session.json # Current session state
checkpoints/ # Phase completion snapshots
artifacts/ # Generated artifacts
requirements/ # Requirements extraction
sessions/ # Past session history
tasks/ # Task assignments
results/ # Completion reports
specs/ # Project specifications
requirements.md
design.md
tasks.md
kanban.md # Task board
./ # Project code (or specified directory)
backend/ # Backend code
frontend/ # Frontend code
docker-compose.yml # Container config
...