agent-architecture-audit

Topics in the source

• Agent Architecture Audit
• When to Activate
• The 12-Layer Stack
• Common Failure Patterns
• 1. Wrapper Regression
• 2. Memory Contamination
• 3. Tool Discipline Failure
• 4. Rendering/Transport Corruption

A diagnostic workflow for agent systems that hide failures behind wrapper layers, stale memory, retry loops, or transport/rendering mutations. MANDATORY for: Releasing any agent or LLM-powered application to production Shipping features with tool calling, memory, or multi-step workflows Agent behavior degrades after adding wrapper layers User reports "the agent is getting worse" or "tools are flaky" Same model works in playground but breaks inside your wrapper Debugging agent behavior for more than 15 minutes without finding root cause Especially critical when: You've added new prompt layers, tool definitions, or memory systems Different agents in your system behave inconsistently The model was fine yesterday but is hallucinating today You suspect hidden repair/retry loops silently mutating responses Do not use for: General code debugging — use agent-introspection-debugging Code review — use language-specific reviewer agents Security scanning — use security-review or security-review/scan Agent performance benchmarking — use agent-eval Writing new features — use the appropriate workflow skill Every agent system has these layers. Any of them can corrupt the answer: | # | Layer | What

This is an excerpt. Refer to the complete source and its current requirements.