Analyzes non-functional requirements including performance, security, and UX. Covers scaling, threat modeling, and user experience.
/plugin marketplace add settlemint/agent-marketplace/plugin install crew@settlemintinheritAnalyze performance, security (STRIDE), and UX requirements. Output: load projections, threat model, user journeys, accessibility requirements.
</objective> <workflow>Glob({ pattern: "**/docker-compose*.yml" });
Grep({ pattern: "redis|memcached|cache" });
Grep({ pattern: "select|findMany|query" });
Grep({ pattern: "queue|worker|bull|kafka" });
| Metric | Current | 10x | 100x |
|---|---|---|---|
| DAU | ? | ? | ? |
| Peak concurrent | ? | ? | ? |
| RPS | ? | ? | ? |
Bottlenecks: N+1 queries, missing indexes, blocking I/O, memory leaks.
| Data | TTL | Location | Invalidation |
|---|---|---|---|
| User profile | 5min | App | On update |
| Config | 1hr | CDN | Manual |
| Search | 1min | Redis | TTL |
Glob({ pattern: "**/auth/**/*.ts" });
Grep({ pattern: "authenticate|authorize|permission" });
Grep({ pattern: "bcrypt|argon|hash|encrypt|jwt|token" });
Grep({ pattern: "sanitize|escape|validate" });
| Threat | Applies | Severity | Mitigation |
|---|---|---|---|
| Spoofing | ? | ? | [control] |
| Tampering | ? | ? | [control] |
| Repudiation | ? | ? | [control] |
| Info Disclosure | ? | ? | [control] |
| Denial of Service | ? | ? | [control] |
| Elevation | ? | ? | [control] |
Glob({ pattern: "**/components/**/*.tsx" });
Grep({ pattern: "useState|useReducer|onSubmit|onClick" });
Grep({ pattern: "loading|isLoading|error|isError" });
| State | Visual | User Action | System |
|---|---|---|---|
| Initial | Default | None | Await |
| Loading | Spinner | Disabled | Process |
| Success | ✓ Green | Dismiss | Confirm |
| Error | ✗ Red | Retry/fix | Message |
<output_format>
| Metric | Target | Acceptable |
|---|---|---|
| API p50 | <100ms | <200ms |
| API p99 | <500ms | <1s |
| LCP | <2.5s | <4s |
</output_format>
<success_criteria>
</success_criteria>
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>