validate

validate is a command for Claude Code from claude-market/marketplace. It costs 5 tokens per session (1,576 once invoked), scanned A, original, MIT.

A command for checking a Claude Code plugin's files, manifest, ownership file, and component folders against required structure rules. A plugin is an add-on that extends Claude Code with commands, skills, agents, or other components.

In plain words
What is it for?
Validating plugin directories, checking `.claude-plugin/plugin.json`, and verifying the required CODEOWNERS and component setup.
Why use it?
It finds missing files, invalid metadata, and structural problems before a plugin is shared or used.

Command for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions Claude Code.

Part of the plugin-builder plugin — 5 commands shipped together

Good fit Validating plugin directories, checking .claude-plugin/plugin.json, and verifying the required CODEOWNERS and component setup.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/claude-market/marketplace/validate
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/claude-market/marketplace

Made for: Claude Code.

Or install plugin-builder, the plugin that ships this one along with the rest of its 5 commands.

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 validate

README.md
[![agentmods](https://agentmods.dev/badge/commands/claude-market/marketplace/validate.svg)](https://agentmods.dev/commands/claude-market/marketplace/validate)
Your own site
<a href="https://agentmods.dev/commands/claude-market/marketplace/validate"><img src="https://agentmods.dev/badge/commands/claude-market/marketplace/validate.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,576 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 $0.00005 $0.01576
Opus 5 $0.00003 $0.00788
Sonnet 5 $0.00001 $0.00315
Haiku 4.5 $0.00001 $0.00158

Measured 8d ago against content hash 253244fadbf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

validate 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.

plugin-builder/commands/validate.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are validating a Claude Code plugin's structure and configuration.

Step 1: Select Plugin

Ask the user which plugin to validate, or use Glob to find all plugins in ./*/.claude-plugin/plugin.json and let them choose.

Step 2: Validation Checks

Perform these validation checks:

Structure Validation

  1. Required files exist:

    • .claude-plugin/plugin.json must exist
    • CODEOWNERS must exist
    • At least one component directory should have content
  2. Directory structure:

    • commands/ for commands (optional - only if commands exist)
    • agents/ for agents (optional - only if agents exist)
    • hooks/ for hooks (optional - only if hooks exist)
    • skills/ for skills (optional - only if skills exist)
    • mcp-servers/ for MCP servers (optional - only if MCP servers exist)
  3. CODEOWNERS validation:

    • File exists at plugin root
    • Contains @claude-market
    • Contains at least one GitHub username
    • Format is valid (pattern: * @org @user name)

Plugin Manifest Validation

Read and validate .claude-plugin/plugin.json:

  1. Required fields:

    • name (string, kebab-case, unique identifier)
    • No other fields are strictly required
  2. Optional metadata fields:

    • version (string, semantic versioning like "1.0.0")
    • description (string, clear and concise)
    • author (object with name, optional email and url)
    • homepage (string, documentation URL)
    • repository (string, source code URL)
    • license (string, license identifier like "MIT")
    • keywords (array of strings for discoverability)
  3. Author field format:

    • If present, author must be an object with a name property
    • Optional properties: email (string), url (string)
    • Correct format: "author": {"name": "John Doe", "email": "[email protected]", "url": "https://example.com"}
    • Incorrect format: "author": "John Doe"
  4. Component path fields (optional):

    List the components your plugin provides:

Read the full file on GitHub · 232 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 · 232 lines · 5 tokens per session scan A 253244fadbf3

Subscribe to this mod's changes

validate is a command published in the GitHub repository claude-market/marketplace (22 stars, last pushed 10mo ago), licensed MIT. It adds 5 tokens to every session and 1,576 once invoked, about $0.0000 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.