nw-review-workflow

nw-review-workflow is a skill for Claude Code from nWave-ai/nWave. It costs 21 tokens per session (734 once invoked), scanned A, original, MIT.

A checklist and scoring process for reviewing coding-agent definitions. It checks their structure, wording, examples, tool access, safety rules, and delegation instructions.

In plain words
What is it for?
Use it to validate agent files, identify revisions needed, and score whether an agent definition meets the review criteria.
Why use it?
It helps reviewers find unclear, oversized, inconsistent, or overly permissive agent instructions before they are used. It also provides a consistent approval decision.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code.

Good fit Use it to validate agent files, identify revisions needed, and score whether an agent definition meets the review criteria.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nwave-ai/nwave/nw-review-workflow
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.

Any agent
npx skills add nWave-ai/nWave --skill nw-review-workflow
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-review-workflow

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-review-workflow"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-review-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 734 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00021 $0.00734
Opus 5 $0.00010 $0.00367
Sonnet 5 $0.00004 $0.00147
Haiku 4.5 $0.00002 $0.00073

Measured 6d ago against content hash d02a9be6fa33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

nw-review-workflow 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 6d 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/skills/nw-review-workflow/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Review Workflow

V2 Validation Checklist (11 Points)

Run against every agent under review. Each item pass/fail.

  1. Frontmatter format: --- delimited YAML with name and description
  2. Size compliance: Under 400 lines; domain knowledge in Skills
  3. Divergence-only: Only behaviors diverging from Claude defaults
  4. Calm language: No "CRITICAL", "MANDATORY", "ABSOLUTE"
  5. Examples present: 3-5 canonical for critical/subtle behaviors
  6. Least privilege tools: Minimum needed in frontmatter
  7. maxTurns set: Present in frontmatter
  8. Platform safety: Via frontmatter/hooks, not prose
  9. Affirmative phrasing: "Do X" not "Don't do Y"
  10. Consistent terminology: One term per concept
  11. Clear delegation: Description states when to delegate

Scoring Methodology

Per-Dimension Scoring

For each of 7 critique dimensions (from critique-dimensions skill):

  • Pass: All checks satisfied
  • Fail: One or more checks not satisfied

Verdict Logic

IF any high-severity dimension fails:
  verdict = "revisions_needed"
ELIF count(medium-severity failures) >= 3:
  verdict = "revisions_needed"
ELSE:
  verdict = "approved"

High-severity: template_compliance, size_and_focus, safety_implementation, priority_validation Medium-severity: divergence_quality, language_and_tone, examples_quality

Evidence Requirements

Every finding includes: Dimension (which of 7) | Severity (high/medium/low) | Finding (observed, with line numbers/counts) | Recommendation (specific fix action)

Common V1 to V2 Migration Issues

Residual Pattern What to Flag
Embedded YAML config blocks Should be frontmatter or removed
activation-instructions section Remove -- Claude Code handles activation
IDE-FILE-RESOLUTION section Remove -- not needed in v2
commands with 10+ entries Reduce to 3-5 focused
Inline embed_knowledge Extract to Skills
5+ "production frameworks" Remove -- platform handles safety
CRITICAL: prefixed instructions Rephrase as calm direct statements
Python/YAML safety code examples Remove -- aspirational, not executable

Read the full file on GitHub · 81 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. 6d ago First seen · 81 lines · 21 tokens per session scan A d02a9be6fa33

Subscribe to this mod's changes

nw-review-workflow is a skill published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 734 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 2026-09-03.

Related

Other skills, from other repositories