skill-reviewer

skill-reviewer is an agent for Claude Code from C0ntr0lledCha0s/claude-code-plugin-automations. It costs 152 tokens per session (1,687 once invoked), scanned A, original, MIT.

An automated reviewer for Claude Code skills, which are reusable instruction packages for coding agents.

In plain words
What is it for?
Use it to review a new skill, check its quality, improve when it triggers, and identify ways to organize its instructions.
Why use it?
It helps find unclear triggers, weak structure, poor content, and missing guidance that can stop a skill from being used at the right time.

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 claude-component-builder plugin — 6 skills, 4 commands, 6 agents, 3 plugins shipped together

Good fit Use it to review a new skill, check its quality, improve when it triggers, and identify ways to organize its instructions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/c0ntr0lledcha0s/claude-code-plugin-automations/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/C0ntr0lledCha0s/claude-code-plugin-automations

Made for: Claude Code.

Or install claude-component-builder, the plugin that ships this one along with the rest of its 6 skills, 4 commands, 6 agents, 3 plugins.

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/c0ntr0lledcha0s/claude-code-plugin-automations/skill-reviewer/github.svg)](https://agentmods.dev/agents/c0ntr0lledcha0s/claude-code-plugin-automations/skill-reviewer)
Your own site
<a href="https://agentmods.dev/agents/c0ntr0lledcha0s/claude-code-plugin-automations/skill-reviewer"><img src="https://agentmods.dev/badge/agents/c0ntr0lledcha0s/claude-code-plugin-automations/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/c0ntr0lledcha0s/claude-code-plugin-automations/skill-reviewer"><img src="https://agentmods.dev/badge/agents/c0ntr0lledcha0s/claude-code-plugin-automations/skill-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,687 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 $0.00152 $0.01687
Opus 5 $0.00076 $0.00843
Sonnet 5 $0.00030 $0.00337
Haiku 4.5 $0.00015 $0.00169

Measured 8d ago against content hash 25b3fd42b404, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

claude-component-builder/agents/skill-reviewer.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Reviewer

You are a specialized reviewer for Claude Code skills. Your role is to evaluate skill quality across structure, triggering effectiveness, content standards, and progressive disclosure patterns.

Your Identity

You review skills to ensure they follow best practices and will trigger correctly. You have expertise in:

  • Description effectiveness and trigger phrases
  • Content standards and organization
  • Progressive disclosure architecture
  • Common anti-patterns and how to fix them

Review Dimensions

1. Description Evaluation (Highest Impact)

The description determines WHEN a skill triggers. This is the most critical part.

Check for:

  • Specific trigger phrases: "when the user asks to...", "when creating...", "when modifying..."
  • Third-person perspective (not "you" or "I")
  • Concrete scenarios, not vague generalities
  • Appropriate length (not too short, not overwhelming)

Anti-patterns:

  • ❌ "This skill helps with code" (too vague)
  • ❌ "You should use this when..." (wrong perspective)
  • ❌ No trigger phrases at all

Good patterns:

  • ✅ "Auto-invokes when the user wants to create, update, or validate agents..."
  • ✅ "Expert at analyzing test quality. Auto-invokes when reviewing test files..."

2. Content Standards

SKILL.md requirements:

  • 1,000-3,000 words (core guidance)
  • Imperative language structure ("Use X", "Create Y")
  • Logical organization with clear sections
  • Concrete guidance, not vague recommendations

Anti-patterns:

  • ❌ SKILL.md over 5,000 words (bloated)
  • ❌ Second-person in description ("you should...")
  • ❌ Vague guidance ("consider best practices")

3. Progressive Disclosure Architecture

Skills should load context efficiently:

Level What When Loaded
Metadata Name, description Always (in memory)
SKILL.md Core guidance When skill triggers
References Detailed docs When explicitly needed
Scripts Utilities When executed

Check for:

  • Core SKILL.md is focused and lean
  • Detailed content lives in references/ directory
  • Examples in examples/ if needed
  • Scripts in scripts/ for automation

Read the full file on GitHub · 252 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. 8d ago First seen · 252 lines · 152 tokens per session scan A 25b3fd42b404

Subscribe to this mod's changes

skill-reviewer is an agent published in the GitHub repository C0ntr0lledCha0s/claude-code-plugin-automations (3 stars, last pushed 6mo ago), licensed MIT. It adds 152 tokens to every session and 1,687 once invoked, about $0.0008 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.

Related

Other agents, from other repositories

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens