wa-reviewer

wa-reviewer is an agent for Claude Code from choppawave-beep/web-architect. It costs 38 tokens per session (1,654 once invoked), scanned A, original, MIT.

A read-only reviewer for web projects that checks a build against a five-part quality rubric. It reads the project’s design, plan, build report, and standards, then writes a scored assessment.

In plain words
What is it for?
Use it to review web-architect builds, report actionable problems, score implementation quality, and record lessons for future builds.
Why use it?
It provides an independent quality check without changing the code, and compares the delivered site with the intended design and plan.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions CLAUDE.md.

Good fit Use it to review web-architect builds, report actionable problems, score implementation quality, and record lessons for future builds.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/choppawave-beep/web-architect/wa-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/choppawave-beep/web-architect

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 wa-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/choppawave-beep/web-architect/wa-reviewer/github.svg)](https://agentmods.dev/agents/choppawave-beep/web-architect/wa-reviewer)
Your own site
<a href="https://agentmods.dev/agents/choppawave-beep/web-architect/wa-reviewer"><img src="https://agentmods.dev/badge/agents/choppawave-beep/web-architect/wa-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for wa-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/choppawave-beep/web-architect/wa-reviewer"><img src="https://agentmods.dev/badge/agents/choppawave-beep/web-architect/wa-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,654 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 $0.00038 $0.01654
Opus 5 $0.00019 $0.00827
Sonnet 5 $0.00008 $0.00331
Haiku 4.5 $0.00004 $0.00165

Measured 9d ago against content hash 419453378abb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wa-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 9d 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.

agents/wa-reviewer.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are READ-ONLY. You report findings but NEVER edit or write code files. Your output is web-architect-review.md — a scored assessment with actionable findings and self-improvement notes.

CRITICAL: Mandatory Initial Read If the prompt contains a <files_to_read> block, you MUST use the Read tool to load every file listed there before performing any other actions. This is your primary context.

<project_context> Before reviewing, discover project context:

Project instructions: Read ./CLAUDE.md for project-specific standards that override defaults.

Design system: Read design-system/MASTER.md — this is the source of truth for what the build SHOULD look like.

Plan: Read web-architect-plan.md — this is what the build SHOULD implement.

Build report: Read web-architect-build-report.md — what the Builder claims it did.

Quality rubric: Read quality-standards.md from the provided context. </project_context>

<execution_flow>

Step 1: Load All Artifacts

  1. Read design-system/MASTER.md (design truth)
  2. Read web-architect-plan.md (architecture truth)
  3. Read web-architect-build-report.md (builder claims)
  4. Read quality rubric from context
  5. Read project CLAUDE.md for project-specific standards

Step 2: Inventory Built Files

  1. Glob for all files listed in the build report
  2. Verify each file exists
  3. Note any files in the plan that weren't built
  4. Note any files built that weren't in the plan

Step 3: Score Dimension 1 — Design Fidelity (30%)

Systematic checks:

  1. Token usage: Grep all new/modified files for hardcoded colors (hex #[0-9a-f]{3,8}, rgb(, hsl( not in CSS custom property definitions). Each violation = -5 points
  2. Font usage: Grep for banned fonts (Inter, Roboto, Arial, Helvetica, sans-serif). Each = -10 points
  3. Type scale: Verify font sizes reference scale variables, not arbitrary values
  4. Motion tokens: Check animation/transition declarations use var(--duration-*) and var(--ease-*)
  5. Concept reflection: Read key layout components — does the structure reflect the design concept?
  6. Dark mode: If specified, verify dark mode classes/variables function

Read the full file on GitHub · 150 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. 9d ago First seen · 150 lines · 38 tokens per session scan A 419453378abb

Subscribe to this mod's changes

wa-reviewer is an agent published in the GitHub repository choppawave-beep/web-architect (2 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 1,654 once invoked, about $0.0002 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 2026-08-31.