golden-principles
**ANALYSIS SKILL** — The agent-first operating principles governing how agents work in this repository. WHEN: "golden principles", "agent behavior rules", "operating philosophy", "principle lookup", "governance invariants". USE FOR: agent behavior rules, operating philosophy, principle lookup, governance invariants. DO NOT USE FOR: Azure infrastructure, code generation, troubleshooting, diagram creation.
git clone --depth 1 https://github.com/jonathan-vella/apex /tmp/golden-principles && cp -r /tmp/golden-principles/.github/skills/golden-principles ~/.claude/skills/golden-principlesSKILL.md
# Golden Principles These 10 principles govern how every agent operates in this repository. They are adapted from the Harness Engineering philosophy for agent-driven infrastructure development. --- ## Rules These 10 principles are the agent operating rules. Detailed explanations follow in [The 10 Principles](#the-10-principles). 1. **Repository Is the System of Record** — all context lives in-repo 2. **Map, Not Manual** — instructions point to deeper sources 3. **Enforce Invariants, Not Implementations** — set boundaries, allow autonomous expression 4. **Parse at Boundaries** — validate inputs and outputs at module edges 5. **AVM-First, Security Baseline Always** — prefer Azure Verified Modules + non-negotiable security baseline 6. **Golden Path Pattern** — prefer shared utilities over hand-rolled helpers 7. **Composable Workflows** — small, well-bounded steps that compose 8. **Human Approval at Critical Gates** — explicit gates between steps 9. **Adversarial Review** — challenger subagents stress-test creative outputs 10. **Continuous Lessons** — capture observations and feed back into the system ## Steps Applying the principles to a new agent or skill: 1. **Read all 10 principles** before designing the agent or skill 2. **For each design decision**, ask which principles apply (typically 2–3 will dominate) 3. **Run the per-principle test** listed in [The 10 Principles](#the-10-principles) 4. **Where a principle conflicts with an implementation choice**, change the implementation — principles are non-negotiable 5. **Document deviations** in an ADR if a principle was knowingly relaxed ## The 10 Principles Each principle has a non-negotiable rule and a quick test for compliance. The canonical detail (full text + per-principle tests + the "How to Apply These Principles" section for agents, contributors, and code review) lives in [`references/principles.md`](references/principles.md). The summary list above is a one-line index; for any decision-making use, load the reference. The two sources are kept in sync — if you spot drift, update the reference and sync the summary. ## Reference Index | Reference | When to Load | | ------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------- | | [`references/principles.md`](references/principles.md) | Applying a principle to a specific design or implementation decision; running the per-principle compliance test |
Guidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references. WHEN: how to instrument app, App Insights SDK, telemetry patterns, what is App Insights, Application Insights guidance, instrumentation examples, APM best practices.
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies, configure AI backend, token metrics, AI cost control, convert API to MCP, import OpenAPI to gateway.
ROUTING SKILL — delegates to specialized diagram skills. USE FOR: any diagram request when the caller does not know which tool to use. Routes to drawio, python-diagrams, or mermaid based on diagram type.
Build and deploy GitHub Copilot SDK apps to Azure. WHEN: build copilot app, create copilot app, copilot SDK, @github/copilot-sdk, scaffold copilot project, copilot-powered app, deploy copilot app, host on azure, azure model, BYOM, bring your own model, use my own model, azure openai model, DefaultAzureCredential, self-hosted model, copilot SDK service, chat app with copilot, copilot-sdk-service template, azd init copilot, CopilotClient, createSession, sendAndWait, GitHub Models API.
Troubleshoot and resolve issues with Azure Messaging SDKs for Event Hubs and Service Bus. Covers connection failures, authentication errors, message processing issues, and SDK configuration problems. WHEN: event hub SDK error, service bus SDK issue, messaging connection failure, AMQP error, event processor host issue, message lock lost, send timeout, receiver disconnected, SDK troubleshooting, azure messaging SDK, event hub consumer, service bus queue issue, topic subscription error, enable logging event hub, service bus logging, eventhub python, servicebus java, eventhub javascript, servicebus dotnet, event hub checkpoint, event hub not receiving messages, service bus dead letter.
Authoritative reference for VS Code Copilot customization mechanisms: instructions, prompt files, custom agents, agent skills, MCP servers, hooks, and plugins. Use when deciding which customization type to use, creating new .instructions.md/.prompt.md/.agent.md/SKILL.md/mcp.json files from scratch, or debugging why a customization is not loading. DO NOT USE FOR: routine file edits where the format is already known.
Provides canonical entity counts from count-manifest.json. Use when agents need to reference how many agents, skills, instructions, or validators exist. Prevents hard-coded counts. WHEN: agent count, skill count, how many agents, how many skills, entity inventory, project statistics.