godmode-engineering · git:20261020.d405f45 · 2026-10-20 · sha256 f3aa4ffbe00e8643

godmode-engineering git:20261020.d405f45A

Immutable. This exact content never changes and is served at /api/v1/blob/f3aa4ffbe00e8643.

---
name: godmode-engineering
description: Domain-Driven Design, strict TypeScript, Clean Architecture. Backend/fullstack implementation and 5-step debugging triage.
category: engineering-method
---

# ⚙️ BDB Engineering Godmode

This skill orchestrates the core logic, domain modeling, and typing constraints of the codebase. It replaces scattershot coding with rigorous, structured engineering methodologies designed for the BDB ecosystem. As an agent, you must execute these principles rigorously across all supported harnesses (Cursor, Claude Code, Agy, Copilot).

## Plan first

Planning starts on the plan canvas, and the human approves it there — not in chat. Pick the template by the work:

- System design or reshaping → `architecture`; one defect → `bugfix`; a data or service move → `migration`; choosing between options → `research`.

```bash
aos-plan-canvas new <template-id> <plan-dir> # scaffold from the choice above
aos-plan-canvas open <plan-dir> --mode bdb-plan-builder # render and open in the browser
aos-plan-canvas await <plan-dir>/plan.mdx # keep listening until the verdict
```

On `approve` of an `architecture`, `bugfix` or `migration` plan, `aos-plan-canvas trail <plan-dir>` derives the agenttrail map for the build; a `research` plan is the artifact itself (no components, no map). The full loop and every template: the `plan-canvas` skill — a plain CLI, identical on every harness.

## 1. Domain Modeling & Type Strictness
Code represents business logic. Do not write implementation details before defining the boundaries.
* **Strict Typing:** `any` is strictly forbidden. Use `unknown` if a type is truly dynamic, and validate it at runtime (e.g., using Zod).
* **Discriminated Unions:** Always use Discriminated Unions (tagged unions) to model state machines. Never rely on multiple optional boolean flags (e.g., `isLoading`, `isError`, `isSuccess`). Instead, use `{ status: 'loading' } | { status: 'error', error: string } | { status: 'success', data: T }`.
* **Immutability:** State must be immutable. Use `.map()`, `.filter()`, and `.reduce()` over standard `for` loops where data transformation is required.

## 2. Codebase Architecture (Clean Architecture)
Do not couple business logic tightly to framework details (like React components or Express routes).
* **Separation of Concerns:** Keep UI logic separate from data fetching. Use custom hooks (in React) or Controllers/Services (in backend) to abstract API calls.
* **Dependency Injection:** Pass dependencies as arguments rather than hardcoding global imports to ensure the logic remains testable.
* **ADR (Architecture Decision Records):** For any major architectural choice (e.g., choosing a new ORM, changing a state management pattern), document the context, decision, and consequences before proceeding.

## 3. Systematic Debugging (The 5-Step Triage)
Do not guess fixes based on a single error log line. If an error occurs, you must execute the 5-step triage:
1. **Reproduce:** Find the exact sequence of inputs that reliably causes the error.
2. **Localize:** Narrow down the error to a specific file or function.
3. **Reduce:** Isolate the function. Can the bug be replicated in a minimal unit test?
4. **Fix:** Implement the precise logic fix without breaking adjacent code.
5. **Guard:** Write a permanent test (Unit or E2E) to prevent regressions.

## 4. Observability & Telemetry
Production code fails. You must ensure we know *why* it failed.
* **Structured Logging:** Do not use `console.log("here")`. Use structured, level-based logging with context (e.g., `logger.error("Failed to fetch user", { userId, error: e.message })`).
* **Error Boundaries:** Ensure the app handles unexpected errors gracefully without crashing the entire process (React Error Boundaries, Node.js global catchers).

## 5. Creator Extension & BDB MediaStorm Governance
This Godmode extends beyond standard software development. It STRICTLY governs creative-tech and show-control workflows (BDB Creator Extension).
* **11-MCP Validation:** When the user invokes `/bdbmediastorm` for TouchDesigner, Unreal Engine, GrandMA3, or Adobe Suite workflows, you MUST validate the signal flow against hardware constraints and MCP availability.
* **Creative-Tech Architecture:** The same principles of Clean Architecture and Modularity apply to node-based graphs (TouchDesigner), Blueprint architectures (Unreal), and DMX showfiles. Do not create monolithic, entangled creative networks.

## Universal Agent Harness Integration
This Godmode is universally compatible and governs all extensions, including the BDB Creator Engine.
* **Cursor:** Auto-injected via `.cursor/rules/godmode-engineering.mdc`.
* **Claude Code:** Reads principles via `CLAUDE.md`.
* **Agy / CLI Agents:** Natively enforced via the prompt orchestrator.
* **Execution:** You (the AI) must silently validate your planned logic against these strict engineering principles before writing code.

## 1. Overview
This skill provides domain-specific logic and rules for its respective BDB pipeline component to ensure standardization across multi-agent workflows.

## 2. When to Use
- Use when specifically requested by the user or triggered by an orchestration agent.
- Use when the current task aligns with the skill's domain.
- Exclude when standard tool execution is sufficient.

## 3. Core Process
1. Read the provided context and ensure preconditions are met.
2. Run the required script or tool and confirm the state change.
3. Verify exit codes, file modifications, or DB counts to guarantee success before reporting completion.

## 4. Common Rationalizations
| Rationalization | Reality |
|---|---|
| "The code change was small, so I skipped updating OpenWiki docs." | Every state change must be reflected in the relevant system records. |
| "The ingest script exited without an error, so the memB index must be updated." | Silent failures happen; explicit verification of the side effect is mandatory. |
| "I'll let the /startcycle proceed without a defined rollback path." | Proceeding without a rollback path corrupts the workflow integrity and safety. |
| "I trust the cached agent registry instead of rescanning after a skill change." | Caches stale out quickly; explicit rescans prevent ghost failures. |

## 5. Red Flags
- Bypassing the verification step after a script execution.
- Proceeding to the next pipeline stage without confirming the previous stage's side effects.
- Ignoring domain-specific constraints listed in this skill.

## 6. Verification
- [ ] Verified script exit codes are explicitly checked.
- [ ] Confirmed target files or database records reflect the expected change.
- [ ] Ensured no silent failures were ignored before reporting success.

---

## App dev Pack Skills

- **agent-tool-builder** — >-
- **agentic-harness-patterns** — >-
- **llm-app-patterns** — "Production-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and industry best practices."
- **llm-structured-output** — >
- **local-llm-expert** — Master local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM Studio. Expert in quantization formats (GGUF, EXL2) and local AI privacy.
- **rag-implementation** — "RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization."
- **prompt-engineer** — "Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)"
- **crewai** — >-
- **vercel-ai-sdk-expert** — "Expert in the Vercel AI SDK. Covers Core API (generateText, streamText), UI hooks (useChat, useCompletion), tool calling, and streaming UI components with React and Next.js."
- **gemini-api-integration** — "Use when integrating Google Gemini API into projects. Covers model selection, multimodal inputs, streaming, function calling, and production best practices."
- **n8n-code-javascript** — Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.
- **n8n-code-python** — Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes.
- **n8n-expression-syntax** — Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, or working with webhook data in workflows.
- **n8n-mcp-tools-expert** — Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
- **n8n-workflow-patterns** — "Proven architectural patterns for building n8n workflows."
- **agent-manager-skill** — Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
- **agent-memory-mcp** — Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
- **subagent-setup** — Configure and synchronize multi-harness subagents (Claude Code, Google Antigravity, OpenCode, ChatGPT Codex CLI) with optional per-harness model overrides and single source of truth in .aos/pipeline.json.

**Install:** `aos store install --pack agents-automation`