system-prompts-and-models-o.../.claude/settings.json
2026-04-16 08:18:43 +03:00

21 lines
1.3 KiB
JSON

{
"theme": "dark",
"projectInstructions": "Follow Dealix Sovereign OS: MASTER_OPERATING_PROMPT.md (canonical), AGENTS.md, CLAUDE.md, docs/ai-operating-model.md, docs/dealix-six-tracks.md, docs/governance/approval-policy.md, docs/governance/technology-radar-tier1.md, docs/enterprise-readiness.md. Agentic by design, governed by policy, proven by evidence. Decision plane = structured cognition; execution plane = durable workflows only. No external commitment without approval + reversibility + evidence. Tier-1 targets (Temporal, OPA, OpenFGA) require ADR docs/adr/0001-tier1-execution-policy-spikes.md exit criteria before production claims.",
"customCommands": [
{
"name": "architecture-map",
"description": "Code-backed discovery brief: constitution files + key app paths (run from repo root).",
"command": "python scripts/architecture_brief.py"
},
{
"name": "canary-check",
"description": "Backend unit tests (Dealix FastAPI) before promotion.",
"command": "cd salesflow-saas/backend && pytest -v --tb=short"
},
{
"name": "security-preflight",
"description": "Launch verification wrapper (staging-style gates; extend with -WithOpenApiGate as needed).",
"command": "powershell -NoProfile -ExecutionPolicy Bypass -File salesflow-saas/verify-launch.ps1"
}
]
}