aod-orchestrate

/aod.orchestrate Skill

Purpose

Orchestrate multiple features from /aod.blueprint output as priority-ordered parallel waves. The skill auto-detects the project, fetches actionable issues, groups them by ICE priority tier, and executes waves sequentially via the batch spawn API with governance checkpoints at tier boundaries.

Flow: Parse flags --> Auto-detect project --> Check idempotency --> Fetch issues --> Plan waves --> Confirm --> Execute waves --> Report completion

---

Step 0: Capture Start Time

Record the orchestration start time for duration calculation in the completion report.

Run the following command via Bash tool and store the result:

date +%s

Store this value as start_time for use in Step 8 (Completion Reporter).

---

Step 1: Parse Arguments

Parse user arguments from the skill invocation.

User Input

$ARGUMENTS

1.1: Parse --issues flag

Check if $ARGUMENTS contains --issues:

1. If $ARGUMENTS contains --issues N,N,N (comma-separated issue numbers):
   • Extract the comma-separated list of issue numbers
   • Set selected_issues to the parsed list of integers
   • Strip --issues N,N,N from $ARGUMENTS (trim extra whitespace)
2. If $ARGUMENTS does NOT contain --issues:
   • Set selected_issues to empty (all issues)

1.2: Parse --dry-run flag

Check if $ARGUMENTS contains --dry-run:

1. If present:
   • Set dry_run = true
   • Strip --dry-run from $ARGUMENTS
2. If not present:
   • Set dry_run = false

1.3: Parse --yes flag

Check if $ARGUMENTS contains --yes:

1. If present:
   • Set auto_confirm = true
   • Strip --yes from $ARGUMENTS
2. If not present:
   • Set auto_confirm = false

---

Step 2: Project Auto-Detection

Resolve the active orchestrator project from local context. Detection follows a priority order with fallback.

2.1: Read config file

Run the following command via Bash tool:

cat .aod/config.json 2>/dev/null