Seed JSON configuration files into database. Use ONCE at BAZINGA session initialization, BEFORE spawning PM.
You are the config-seeder skill. Your role is to seed JSON configuration files into database tables at session start.
This skill seeds workflow configuration from JSON files into database tables:
workflow/transitions.json → workflow_transitions tableworkflow/agent-markers.json → agent_markers table_special_rules from transitions.json → workflow_special_rules tableNote: In dev mode, bazinga/config is a symlink to ../workflow for path compatibility.
bazinga/bazinga.db exists)workflow/transitions.json (source) or bazinga/config/transitions.json (symlink)workflow/agent-markers.json (source) or bazinga/config/agent-markers.json (symlink)When invoked, you must:
Use the unified initialization script that handles DB + config in one step:
python3 .claude/skills/bazinga-db/scripts/init_session.py --session-id "{session_id}"
This script:
Alternative: Call seed script directly (requires DB to exist first):
python3 .claude/skills/config-seeder/scripts/seed_configs.py --all
With auto-init: Initialize DB if missing:
python3 .claude/skills/config-seeder/scripts/seed_configs.py --all --auto-init-db
Expected output on success:
Seeded 45 transitions
Seeded 7 agent marker sets
Seeded 5 special rules
✅ Config seeding complete
If successful:
If failed:
State machine rules for routing:
developer + READY_FOR_QA → qa_expertdeveloper + READY_FOR_REVIEW → tech_leadqa_expert + PASS → tech_leadtech_lead + APPROVED → merge → check phaseRequired markers per agent type:
developer: "NO DELEGATION", "READY_FOR_QA", "BLOCKED", etc.qa_expert: "PASS", "FAIL", "Challenge Level", etc.tech_lead: "APPROVED", "CHANGES_REQUESTED", etc.Workflow modification rules:
testing_mode_disabled: Skip QA entirelytesting_mode_minimal: Skip QA Expertescalation_after_failures: Escalate to SSE after 2 failuressecurity_sensitive: Force SSE + mandatory TL reviewresearch_tasks: Route to RE with limited parallelismReturn success/failure message. No structured output needed.
| Error | Meaning |
|---|---|
| Config file not found | JSON files missing - check workflow/ (or bazinga/config/ symlink) |
| Database not found | Run init_db.py first |
| Insert failed | Database schema mismatch - run migration |
If seeding fails, orchestration CANNOT proceed. The prompt-builder and workflow-router skills depend on these database tables.