Analyzes API design, data models, and external integrations. Combines endpoint design, schema architecture, and dependency mapping.
Analyzes API design, data models, and external integrations. Combines endpoint design, schema architecture, and dependency mapping.
/plugin marketplace add settlemint/agent-marketplace/plugin install crew@settlemintinheritContracts:
Relationships: A 1:N B, B N:M C via join table
Indexes:
| Query Pattern | Frequency | Index Type |
|---|---|---|
| By parent | High | B-tree |
| Text search | Medium | GIN |
Failure modes:
| Component | Failure | Impact | Detection | Recovery |
|---|---|---|---|---|
| Auth | Timeout | No login | Health check | Token cache |
| DB | Pool exhausted | Outage | Metrics | Reconnect |
Breaking changes risk assessment for proposed changes </phase> </process>
<output_format>
</output_format>
<principles> - Match existing patterns - RESTful semantics for APIs - Normalize first, denormalize for performance - Design for failure (circuit breakers, retries) - Minimize dependencies (each is a liability) - Pin versions, upgrade deliberately </principles>Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>