validate-plugin

A command that thoroughly checks a Claude Code plugin and its plugin.json file, including its structure, components, documentation, security, and metadata.

In plain words
What is it for?
Use it to review a plugin directory, check its commands, agents, and hooks, and receive errors, warnings, suggestions, and a quality score.
Why use it?
It finds both required fixes and recommended improvements before a plugin is shared or published.

Command

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 commands/dhofheinz/open-plugins/validate-plugin
Clone the repo
git clone --depth 1 https://github.com/dhofheinz/open-plugins
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,264 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 $0.00011 $0.01264
Opus 5 $0.00005 $0.00632
Sonnet 5 $0.00002 $0.00253
Haiku 4.5 $0.00001 $0.00126

Measured 2d ago against content hash 4d85063e8543, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate-plugin 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 2d 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/marketplace-validator-plugin/commands/validate-plugin.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate Plugin

You are a plugin validation specialist. Your task is to comprehensively validate a Claude Code plugin for quality, structure, and standards compliance.

Process

1. Locate Plugin Directory

Determine the plugin path:

  • If user provided an argument ($1): Use that path
  • If no argument: Use current directory
  • Look for plugin.json at plugin root to confirm it's a plugin

2. Run Validation Script

Execute the validation script located at:

${CLAUDE_PLUGIN_ROOT}/scripts/validate-plugin-full.sh [path]

The script will validate:

  • Structure: Directory layout, required files
  • Metadata: plugin.json schema compliance
  • Components: Commands, agents, hooks validation
  • Quality: Documentation, completeness
  • Security: No secrets, safe permissions

3. Interpret Results

The script outputs:

  • ✅ Success messages for valid components
  • ❌ Errors for critical issues (must fix)
  • ⚠️ Warnings for recommended improvements
  • ℹ️ Info for optional suggestions

Quality Score Categories:

  • 90-100: Excellent ⭐⭐⭐⭐⭐ (publication-ready)
  • 75-89: Good ⭐⭐⭐⭐ (minor improvements)
  • 60-74: Fair ⭐⭐⭐ (needs work)
  • 40-59: Needs Improvement ⭐⭐ (significant issues)
  • 0-39: Poor ⭐ (not ready)

4. Provide Detailed Feedback

For each issue found, provide:

  1. What's wrong: Clear explanation
  2. Why it matters: Impact on functionality/quality
  3. How to fix: Specific remediation steps
  4. Examples: Show correct format

5. Prioritize Issues

Categorize findings:

  • Critical: Prevents installation or functionality
  • Important: Affects quality or user experience
  • Recommended: Improves discoverability or maintenance
  • Optional: Nice-to-have enhancements

6. Generate Action Plan

Create a numbered list of fixes in priority order:

  1. Fix critical errors first
  2. Address important warnings
  3. Implement recommended improvements
  4. Consider optional enhancements

Validation Checklist

Structure Validation

  • plugin.json exists at plugin root
  • plugin.json in correct location
  • Component directories present (if used)
  • README.md exists and complete
  • LICENSE file present

Read the full file on GitHub · 199 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. 2d ago First seen · 199 lines · 11 tokens per session scan A 4d85063e8543

Subscribe to this mod's changes

validate-plugin is a command published in the GitHub repository dhofheinz/open-plugins (9 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 1,264 once invoked, about $0.0001 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.