Enforces a 4-phase architecture design workflow by reading `.arch/state.json` on every request to gate responses by phase. Phase 1 extracts and validates requirements from PRDs; Phase 2 selects architecture patterns and establishes high-level structure; Phase 3 designs and accepts components sequentially; Phase 4 finalises and documents the solution. Use when discussing system design, solution architecture, PRD analysis, component design, technology selection, or architecture patterns — distinct from general coding help by its strict phase-gating, anti-pattern detection, and state-tracked component acceptance.
93
97%
Does it follow best practices?
Impact
89%
1.07xAverage score across 5 eval scenarios
Passed
No known issues
{
"context": "Tests whether the agent identifies the full set of anti-patterns present in a flawed architecture proposal: unjustified technology, copy-paste architecture from large tech companies, over-engineering relative to team size, missing NFRs, and vague deferrals — without simply approving the proposal.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Flags unjustified technology",
"description": "architecture-review.md flags Kafka (or the event streaming choice) as mentioned without justification beyond citing Netflix/Uber",
"max_score": 12
},
{
"name": "Asks for alternatives",
"description": "architecture-review.md asks what alternatives to the chosen technology were considered",
"max_score": 10
},
{
"name": "Flags over-engineering",
"description": "architecture-review.md explicitly flags the mismatch between 14 services and a team of 3, questioning whether all components are necessary",
"max_score": 12
},
{
"name": "Flags missing availability NFR",
"description": "architecture-review.md flags that availability or uptime requirements are absent or marked TBD",
"max_score": 10
},
{
"name": "Flags missing security NFR",
"description": "architecture-review.md flags that security or compliance requirements (e.g. HIPAA) are deferred without a plan",
"max_score": 10
},
{
"name": "Flags missing monitoring NFR",
"description": "architecture-review.md flags that monitoring or alerting requirements are absent or vague",
"max_score": 10
},
{
"name": "Challenges deferral",
"description": "architecture-review.md challenges the security/HIPAA deferral with a specific question about the worst-case impact or quantifies the risk of deferring",
"max_score": 13
},
{
"name": "Challenges copy-paste",
"description": "architecture-review.md questions whether the architecture was chosen because it resembles large-scale companies (Netflix, Uber, Airbnb) rather than because it fits the team's actual requirements",
"max_score": 13
},
{
"name": "Does not approve",
"description": "architecture-review.md does NOT validate or endorse the proposal without raising substantive concerns",
"max_score": 10
}
]
}