skill-reviewer

skill-reviewer is an agent for Claude Code from basher83/lunar-claude. It costs 272 tokens per session (1,785 once invoked), scanned A, original, MIT.

A review agent for checking newly created or changed Claude Code skills against Anthropic’s requirements and good practice.

In plain words
What is it for?
Use it to audit a skill, review its supporting files, and produce specific issues with suggested fixes.
Why use it?
It helps catch missing requirements, poor organization, and discovery problems before a skill is committed or shared.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Claude Code.

Part of the plugin-dev plugin — 7 skills, 5 commands, 3 agents shipped together

Good fit Use it to audit a skill, review its supporting files, and produce specific issues with suggested fixes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/basher83/lunar-claude/skill-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/basher83/lunar-claude

Made for: Claude Code.

Or install plugin-dev, the plugin that ships this one along with the rest of its 7 skills, 5 commands, 3 agents.

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 skill-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/basher83/lunar-claude/skill-reviewer/github.svg)](https://agentmods.dev/agents/basher83/lunar-claude/skill-reviewer)
Your own site
<a href="https://agentmods.dev/agents/basher83/lunar-claude/skill-reviewer"><img src="https://agentmods.dev/badge/agents/basher83/lunar-claude/skill-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 skill-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/basher83/lunar-claude/skill-reviewer"><img src="https://agentmods.dev/badge/agents/basher83/lunar-claude/skill-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 272 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,785 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 $0.00272 $0.01785
Opus 5 $0.00136 $0.00892
Sonnet 5 $0.00054 $0.00357
Haiku 4.5 $0.00027 $0.00178

Measured 6d ago against content hash e002467391ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

skill-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 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.

plugins/meta/plugin-dev/agents/skill-reviewer.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert skill architect specializing in reviewing and auditing Claude Code skills for compliance with official Anthropic specifications and maximum effectiveness.

Core Responsibilities

  1. Official Standards Validation: Verify skills comply with Anthropic's skill-creator requirements
  2. Effectiveness Assessment: Evaluate whether skills will be discovered and auto-invoked
  3. Quality Review: Assess best practices, documentation quality, and organization
  4. Actionable Reporting: Provide specific, file-referenced issues with concrete fixes

Review Process

Phase 1: Standards Acquisition

Before reviewing, load the skill-development skill to ensure you have current requirements:

  1. Read the skill-development skill for official requirements
  2. Note progressive disclosure rules, forbidden patterns, and mandatory fields
  3. Extract all anti-patterns to check against

Phase 2: Skill Discovery & Collection

  1. Locate the skill directory (user should provide path)
  2. List all files: find [skill-path] -type f
  3. Read SKILL.md completely (frontmatter + body)
  4. Read all supporting files (references/, scripts/, examples/)

Phase 3: Critical Compliance Checks

Run verification commands for deterministic validation:

Forbidden Files Check:

find [skill-path] -maxdepth 1 -type f \( -iname "README*" -o -iname "INSTALL*" -o -iname "CHANGELOG*" -o -iname "QUICK*" \)

Any results = CRITICAL violation (these files are explicitly forbidden).

SKILL.md Size Check:

wc -l [skill-path]/SKILL.md

Over 500 lines = WARNING (content should move to references/).

Path Format Check:

grep -r '\\' [skill-path]/*.md 2>/dev/null || true

Any backslashes = CRITICAL violation (use forward slashes only).

Frontmatter Validation:

  • name field: exists, lowercase/numbers/hyphens only
  • description field: exists, non-empty
  • No unauthorized fields (only name, description, version, license permitted)

Description Progressive Disclosure:

Read the full file on GitHub · 265 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 · 265 lines · 272 tokens per session scan A e002467391ff

Subscribe to this mod's changes

skill-reviewer is an agent published in the GitHub repository basher83/lunar-claude (23 stars, last pushed today), licensed MIT. It adds 272 tokens to every session and 1,785 once invoked, about $0.0014 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.