config-reviewer

config-reviewer is an agent for Claude Code from wesammustafa/Claude-Code-Everything-You-Need-to-Know. It costs 77 tokens per session (665 once invoked), scanned B, original, MIT.

A read-only checker for a repository's shared Claude Code settings, rules, plugins, and marketplace definitions. It looks for overly broad permissions, exposed secrets, personal machine settings, and broken plugin references, then reports severity.

In plain words
What is it for?
Use it to audit .claude configuration and plugin marketplace entries before a commit or review.
Why use it?
It helps catch unsafe or machine-specific configuration before it is committed to the repository. It reports findings without changing files.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it to audit .claude configuration and plugin marketplace entries before a commit or review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wesammustafa/claude-code-everything-you-need-to-know/config-reviewer
About the project

Claude Code: Everything You Need to Know is a practical guide to using Claude Code, an AI coding assistant that can be extended with commands, skills, hooks, subagents, workflows, and external tool servers. Developers use it to learn Claude Code from basic prompting through team and automation setups. The catalogue entries are examples of the guide's Claude Code extensions and workflows.

wesammustafa/Claude-Code-Everything-You-Need-to-Know · 3,516 stars · on GitHub

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/wesammustafa/Claude-Code-Everything-You-Need-to-Know

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 config-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/wesammustafa/claude-code-everything-you-need-to-know/config-reviewer/github.svg)](https://agentmods.dev/agents/wesammustafa/claude-code-everything-you-need-to-know/config-reviewer)
Your own site
<a href="https://agentmods.dev/agents/wesammustafa/claude-code-everything-you-need-to-know/config-reviewer"><img src="https://agentmods.dev/badge/agents/wesammustafa/claude-code-everything-you-need-to-know/config-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 config-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/wesammustafa/claude-code-everything-you-need-to-know/config-reviewer"><img src="https://agentmods.dev/badge/agents/wesammustafa/claude-code-everything-you-need-to-know/config-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 665 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00077 $0.00665
Opus 5.5 $0.00031 $0.00266
Sonnet 5.5 $0.00015 $0.00133
Haiku 4.5 $0.00008 $0.00067

Measured today against content hash af6c77bfaebb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

config-reviewer scanned grade B with 1 finding 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 today.

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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

description: Reviews the repository's shared Claude Code configuration (.claude/settings.json, CLAUDE.md, .claude/rules/, .mcp.json and the team marketplace) for allow rules that are too broad, secrets, personal settings
solutions/a-6/team-marketplace/plugins/team-kit/agents/config-reviewer.md · 26 lines

What it actually says

You review a repository's shared Claude Code configuration. You never change files: you report what you find, and the main conversation decides what to fix.

  1. Read the shared files that exist: .claude/settings.json, CLAUDE.md, the files in .claude/rules/, .mcp.json, and each marketplace that .claude/settings.json declares by a local path, with the plugin.json and components of each plugin it lists. If your task names other files, read those too.
  2. Check for:
    • permissions: allow rules broader than the team needs, such as a bare Bash, Write or Edit, or a Bash rule with a wildcard over a whole command family; and a missing Read deny rule for .env;
    • secrets: keys, tokens or passwords in any of these files;
    • personal settings in the repository: a CLAUDE.local.md that .gitignore doesn't list, or a path that exists only on one person's machine, such as one under a home folder;
    • plugins: an enabledPlugins entry set to true whose marketplace no extraKnownMarketplaces entry declares, other than claude-plugins-official and the @inline, @skills-dir and @synced ids, which take no marketplace; a marketplace path that isn't relative; a marketplace entry whose relative-path source contains ..; or an entry name that differs from the name in its plugin's plugin.json;
    • hooks: a hook command that names a script missing from the repository.
  3. Report findings grouped as Must fix, Should fix and Consider. For each one give the file and line, the problem, and a concrete fix. If you find nothing, say so and say what you checked.

Keep the report short: no praise and no summary of the files.

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. today First seen · 26 lines · 77 tokens per session scan B af6c77bfaebb

Subscribe to this mod's changes

config-reviewer is an agent published in the GitHub repository wesammustafa/Claude-Code-Everything-You-Need-to-Know (3,516 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 665 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-01.

Related

Other agents, from other repositories

guide-reviewer

Vérifier accuracy factuelle, détecter marketing speak, checker anti-AI markers (em dashes, staccato), tone Bold Guy dans le guide ou une section. Retourne une liste de findings classés par type. Use when reviewing newly added guide content before committing.

FlorianBruniaux/claude-code-ultimate-guide · 61 tokens

claude-code-guide

Expert on the Claude Code Ultimate Guide. Use when answering questions about Claude Code features, workflows, configuration, hooks, agents, MCP servers, costs, and best practices. Searches the guide before answering. Cites file + line sources.

FlorianBruniaux/claude-code-ultimate-guide · 52 tokens

whitepaper-journalist

Review d'un livre blanc dans le style d'un journaliste expérimenté. Analyse critique, style direct, recommandations éditorialistes. Utiliser pour avoir un regard externe avant publication.

FlorianBruniaux/claude-code-ultimate-guide · 41 tokens

whitepaper-density

Analyse le ratio valeur/remplissage d'un livre blanc. Identifie la rhétorique creuse, le padding, et les sections sans substance. Utiliser pour densifier un whitepaper avant publication.

FlorianBruniaux/claude-code-ultimate-guide · 45 tokens

whitepaper-coherence

Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.

FlorianBruniaux/claude-code-ultimate-guide · 39 tokens

evidence-reviewer

Use after local checks to review whether Proofpack release claims match retained evidence.

FlorianBruniaux/claude-code-ultimate-guide · 20 tokens