// Audit producer-consumer alignment in EstateWise when REST, tRPC, MCP, gRPC, A2A, or shared payloads may have changed. Use when one package's change could silently break another package, tool, or doc set.
Work on EstateWise MCP, agentic-ai, web-grounding, token flows, and A2A integrations. Use when changing tool behavior, orchestration, runtime flags, MCP wrappers, HTTP/A2A endpoints, or AI integration paths.
Extend or audit Codex support in the EstateWise repository. Use when changing .codex config, .codex/rules, .agents/skills, AGENTS.md layering, multi-agent roles, project guidance discovery, or Codex-specific documentation and workflows.
Execute production-safe code changes in the EstateWise monorepo. Use when implementing or fixing behavior in backend, frontend, MCP, agentic-ai, gRPC, deployment-control, tests, or repo docs. Do not use for pure brainstorming, skill installation, or work outside this repository.
Run or debug the EstateWise local environment. Use when setting up services, choosing the smallest service combination, checking local endpoints, or troubleshooting environment/config issues. Do not use for routine code implementation unless local run/debugging is the main task.
Work on EstateWise deployment-control, Docker, Kubernetes, Helm, Terraform, Jenkins, and cloud deployment assets. Use for infrastructure and operational workflow changes, not ordinary application feature work.
Review EstateWise changes for correctness, regressions, security issues, contract mismatches, operational risk, and missing tests. Use for PR review, diff review, bug hunts, and branch-vs-main analysis. Do not use for implementation tasks unless the user asks for fixes after findings are reported.
| name | estatewise-contracts |
| description | Audit producer-consumer alignment in EstateWise when REST, tRPC, MCP, gRPC, A2A, or shared payloads may have changed. Use when one package's change could silently break another package, tool, or doc set. |
Use this skill whenever a change could affect another package or service, even if the code edit is small.
backend/src/routes/, backend/src/controllers/, swagger annotations, backend/README.mdfrontend/lib/api.ts plus direct fetch(...) usage in frontend/pages/frontend/server/api/routers/, frontend/pages/api/trpc/[trpc].ts, frontend/lib/trpc.tsxmcp/src/tools/*.ts, mcp/src/server.ts, mcp/src/client.ts, mcp/README.mdagentic-ai/src/http/server.ts, agentic-ai/src/a2a/, agentic-ai/README.mdgrpc/proto/market_pulse.proto, grpc/src/services/, grpc/README.mdIf a backend endpoint, query param, auth rule, or payload changes, inspect:
frontend/lib/api.tsfrontend/pages/mcp/src/tools/If a local tRPC router changes, inspect:
frontend/server/api/routers/frontend/lib/trpc.tsxIf an MCP tool name, schema, or output changes, inspect:
mcp/src/client.tsagentic-ai/src/lang/tools.tsmcp/README.mdIf agentic-ai server endpoints or task semantics change, inspect:
agentic-ai/src/http/server.tsagentic-ai/src/a2a/mcp/src/tools/a2a.tsagentic-ai/README.mdmcp/README.mdIf the proto changes, inspect:
grpc/src/services/grpc/src/server.tsUse targeted searches like:
rg -n "estatewise-backend\\.vercel\\.app|API_BASE_URL" frontendrg -n "/api/|fetch\\(" frontend/pages frontend/librg -n "name:\\s*\"<tool>\"|callTool\\(|client:call" mcp agentic-airg -n "/run|/run/stream|a2a|agent-card|tasks\\." agentic-ai mcprg -n "market_pulse|MarketPulseService" grpcREST contract change:
cd backend && npm run build && npm run testcd frontend && npm run build && npm run test when frontend callers changedcd mcp && npm run build && npm run client:call -- <tool> '<json>' when MCP wrappers changedtRPC contract change:
cd frontend && npm run build && npm run testMCP contract change:
cd mcp && npm run buildcd mcp && npm run client:call -- <tool> '<json>'cd agentic-ai && npm run build when consumed thereA2A/HTTP contract change:
cd agentic-ai && npm run builda2a.* bridge when relevantgRPC contract change:
cd grpc && npm run build && npm run test && npm run proto:checkState: