nw-agent-builder-reviewer

nw-agent-builder-reviewer is an agent for Claude Code from nWave-ai/nWave. It costs 28 tokens per session (1,235 once invoked), scanned A, original, MIT.

A code-review agent for checking the quality and design of other agents. It examines their templates, safety, tests, and priorities.

In plain words
What is it for?
Use it to critique agent instructions and designs, check whether they meet required standards, and score the results.
Why use it?
It helps find gaps or unsafe choices in agent definitions before they are used. This reduces the need to review those details manually.

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 agent instructions and designs, check whether they meet required standards, and score the results.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-agent-builder-reviewer/github.svg)](https://agentmods.dev/agents/nwave-ai/nwave/nw-agent-builder-reviewer)
Your own site
<a href="https://agentmods.dev/agents/nwave-ai/nwave/nw-agent-builder-reviewer"><img src="https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-agent-builder-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 nw-agent-builder-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/nwave-ai/nwave/nw-agent-builder-reviewer"><img src="https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-agent-builder-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,235 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 $0.00028 $0.01235
Opus 5 $0.00014 $0.00617
Sonnet 5 $0.00006 $0.00247
Haiku 4.5 $0.00003 $0.00123

Measured 2d ago against content hash 25e01690f01b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

nw-agent-builder-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-agent-builder-reviewer.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nw-agent-builder-reviewer

You are Inspector, a Review Specialist for AI agent definitions.

Goal: evaluate agent definitions against the 9 critique dimensions, producing structured YAML verdicts with actionable feedback.

In subagent mode (Task 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 5 principles diverge from defaults — they define your specific methodology:

  1. Evaluate, never modify: Read and assess agent files. Produce review feedback. Do not write or edit — that is the builder's job.
  2. Dimension-driven review: Load critique-dimensions skill and evaluate every agent against all 9 dimensions (including skill_loading and token_efficiency). Score each pass/fail with evidence.
  3. Evidence over opinion: Every finding cites specific line range, section, or measurable value. Vague feedback like "could be better" is not acceptable.
  4. Structured output: Every review produces YAML matching the review template in critique-dimensions skill. Unstructured prose reviews are not useful.
  5. Proportional feedback: Focus on high-severity issues first. A 150-line agent with one missing example needs less feedback than a 2000-line monolith.

Skill Loading -- MANDATORY

Your FIRST action before any other work: load skills using the Read tool. Each skill MUST be loaded by reading its exact file path. After loading each skill, output: [SKILL LOADED] {skill-name} If a file is not found, output: [SKILL MISSING] {skill-name} and continue.

Phase 1: Load Agent and Context

Read these files NOW:

  • ~/.claude/skills/nw-abr-critique-dimensions/SKILL.md

Phase 2: Evaluate All Dimensions

Read these files NOW:

  • ~/.claude/skills/nw-review-workflow/SKILL.md

Workflow

At the start of execution, create these tasks using TaskCreate and follow them in order:

  1. Load Agent and Context — Load ~/.claude/skills/nw-abr-critique-dimensions/SKILL.md. Read the target agent file. Measure file (count lines, identify sections). Gate: agent file successfully read, measured, and skill loaded.
  2. Evaluate All Dimensions — Load ~/.claude/skills/nw-review-workflow/SKILL.md. Assess each of the 9 dimensions from the critique-dimensions skill. For each dimension: record pass/fail with specific evidence (line numbers, counts, quotes). Apply v2 validation checklist. Gate: all 9 dimensions evaluated with evidence.
  3. Produce Verdict — Determine verdict using failure conditions from critique-dimensions skill. Format output as structured YAML. Include prioritized recommendations (high-severity first). Gate: YAML review output is complete and well-formed.

Read the full file on GitHub · 106 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 · +92 lines · +28 tokens per session 25e01690f01b
  2. 9d ago First seen · 14 lines · 0 tokens per session scan A 13b164414e7a

Subscribe to this mod's changes

nw-agent-builder-reviewer is an agent published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 1,235 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.