plugin-validator

A validation agent for checking the structure and files of a coding-agent plugin, including its plugin.json manifest.

In plain words
What is it for?
Use it to verify plugin manifests, discoverable component folders, commands, agents, and related plugin files.
Why use it?
It helps catch invalid metadata, missing directories, malformed commands, and incorrectly defined agents or skills before the plugin is used.

Agent

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.

agentmods
npx agentmods add agents/vibe-marketer/plugins-and-skills/plugin-validator
Clone the repo
git clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-skills
Per session 214 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,423 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00214 $0.01423
Opus 5 $0.00107 $0.00711
Sonnet 5 $0.00043 $0.00285
Haiku 4.5 $0.00021 $0.00142

Measured yesterday against content hash da5f12ba8681, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugin-validator 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 yesterday.

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.

create-plugins/agents/plugin-validator.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<step_2 name="validate_manifest"> Check .claude-plugin/plugin.json:

  • Valid JSON syntax (use Bash with jq or Read + parse)
  • Required field: name (kebab-case, no spaces)
  • Optional fields if present: version (semver X.Y.Z), description (non-empty), author, mcpServers
  • Flag unknown fields as warnings (not errors) </step_2>

<step_3 name="validate_directories"> Use Glob to find component directories:

  • commands/ for slash commands
  • agents/ for agent definitions
  • skills/ for skill directories
  • hooks/hooks.json for hooks
  • shared/ for shared resources
  • Verify auto-discovery paths work </step_3>

<step_4 name="validate_commands"> For each file in commands/**/*.md:

  • YAML frontmatter present (starts with ---)
  • description field exists and is non-empty
  • argument-hint format correct if present
  • allowed-tools is array if present
  • Markdown body content exists
  • Check for naming conflicts </step_4>

<step_5 name="validate_agents"> For each file in agents/**/*.md:

  • Frontmatter with name, description, model
  • Name format: lowercase, hyphens, 3-50 chars
  • Description includes <example> blocks
  • Model is valid: inherit, sonnet, opus, haiku
  • Color is valid if present: blue, cyan, green, yellow, magenta, red
  • System prompt exists and is substantial (>100 chars) </step_5>

<step_6 name="validate_skills"> For each skills/*/SKILL.md:

  • SKILL.md file exists in skill directory
  • YAML frontmatter with name and description
  • Description is concise and clear
  • Body uses pure XML structure (no markdown headings)
  • Required tags present: <objective>, <quick_start>, <success_criteria>
  • Referenced files in references/ actually exist </step_6>

<step_7 name="validate_hooks"> If hooks/hooks.json exists:

  • Valid JSON syntax
  • Valid event names (PreToolUse, PostToolUse, Stop, etc.)
  • Each hook has matcher and hooks array
  • Hook type is command or prompt
  • Commands reference existing scripts with ${CLAUDE_PLUGIN_ROOT} </step_7>

<step_8 name="validate_mcp"> If .mcp.json or mcpServers in manifest:

  • Valid JSON syntax
  • stdio servers have command field
  • sse/http/ws servers have url field
  • Check ${CLAUDE_PLUGIN_ROOT} usage for portability </step_8>

<step_9 name="check_organization">

  • No unnecessary files (node_modules, .DS_Store, etc.)
  • .gitignore present if needed
  • Consistent naming conventions throughout </step_9>

<step_10 name="security_checks">

  • No hardcoded credentials in any files
  • MCP servers use HTTPS/WSS not HTTP/WS
  • Hooks don't have obvious security issues
  • No secrets in example files </step_10>

<output_format>

Plugin Validation Report

Read the full file on GitHub · 179 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. yesterday First seen · 179 lines · 214 tokens per session scan A da5f12ba8681

Subscribe to this mod's changes

plugin-validator is an agent published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 214 tokens to every session and 1,423 once invoked, about $0.0011 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens