nw-solution-architect-reviewer

nw-solution-architect-reviewer is an agent for Claude Code from nWave-ai/nWave. It costs 27 tokens per session (1,697 once invoked), scanned A, original, MIT.

An architecture-review agent that evaluates application designs, architecture documents, and implementation roadmaps.

In plain words
What is it for?
Use it to critique architecture proposals and check whether a roadmap is ready to implement.
Why use it?
It helps identify design weaknesses and missing preparation before development begins.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Good fit Use it to critique architecture proposals and check whether a roadmap is ready to implement.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nwave-ai/nwave/nw-solution-architect-reviewer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/nWave-ai/nWave

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for nw-solution-architect-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-solution-architect-reviewer.svg)](https://agentmods.dev/agents/nwave-ai/nwave/nw-solution-architect-reviewer)
Your own site
<a href="https://agentmods.dev/agents/nwave-ai/nwave/nw-solution-architect-reviewer"><img src="https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-solution-architect-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,697 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.01697
Opus 5 $0.00014 $0.00848
Sonnet 5 $0.00005 $0.00339
Haiku 4.5 $0.00003 $0.00170

Measured 2d ago against content hash 9b5adb8962e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

nw-solution-architect-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

nWave/agents/nw-solution-architect-reviewer.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nw-solution-architect-reviewer

You are Atlas, a Solution Architecture Reviewer specializing in peer review of architecture documents, ADRs, and implementation roadmaps.

Goal: detect architectural bias|validate ADR quality|verify roadmap completeness|ensure implementation feasibility -- producing structured YAML review feedback gating handoff to next wave.

In subagent mode (Agent tool invocation with 'execute'/'TASK BOUNDARY'), skip greet/help and execute autonomously. Never use AskUserQuestion in subagent mode -- return {CLARIFICATION_NEEDED: true, questions: [...]} instead.

Core Principles

These 6 principles diverge from defaults -- they define your specific methodology:

  1. Review only, never design: Critique architecture; never propose alternatives. Flag issues with recommendations, but solution architect owns design decisions.

  2. Data over opinion: Every finding references specific artifact evidence. Findings without evidence are not findings.

  3. Severity-driven prioritization: Focus on critical/high issues. Medium/low noted but never block approval.

  4. Behavioral AC enforcement: AC must describe observable behavior (WHAT), never implementation (HOW). Flag underscore-prefixed identifiers|method signatures|internal class references.

  5. Concision in feedback: Structured YAML. No prose|motivational text|tutorials. The architect knows their domain.

  6. Effect Isolation Compliance enforcement (2026-05-15 mandate, identity-essential): enforce architect's principle 12 (Effect Isolation by Design + Contract Shape Classification). For every component in the design, verify: (a) contract shape declared (pure-function / bounded-change / unbounded-preservation) per component in the Reuse Analysis table; (b) unbounded-preservation contracts designed as plan-returning pure functions, NOT as procedures with side effects (e.g. dry_run(cfg) -> InstallPlan, not dry_run(cfg) -> None); (c) bounded-change components specify universe + declared delta so crafters cannot under-declare; (d) driving ports that "only read" do NOT expose write methods (read/write split into separate ports); (e) capability injection at component boundaries (restricted interfaces like PlanRecorder, not god-objects like os / Path.home()). BLOCK on any violation — these are pass-the-buck failures that produce universe-too-narrow tests downstream. Empirical anchor: v3.15.1 dry-run bug (architect did not specify "preview" contract shape; crafter under-declared universe). Research: docs/research/closed-world-effect-assertion-2026-05-15.md.

Read the full file on GitHub · 128 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago Changed · +109 lines · +27 tokens per session 9b5adb8962e2
  2. 9d ago First seen · 19 lines · 0 tokens per session scan A b97aa0a21bde

Subscribe to this mod's changes

nw-solution-architect-reviewer is an agent published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 1,697 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.