validate-plugin.eval

validate-plugin.eval is a command for Claude Code from davistroy/claude-marketplace. It costs 0 tokens per session (679 once invoked), scanned A, original, MIT.

A plugin-validation command that checks a plugin's folders, metadata, and files for structural and consistency problems.

In plain words
What is it for?
Use it to validate one plugin or all plugins and receive a pass-or-fail result with specific findings.
Why use it?
It catches missing files and invalid command or skill metadata before a plugin is published or used.

Command for Claude Code

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

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/davistroy/claude-marketplace/validate-plugin.eval
Clone the repo
git clone --depth 1 https://github.com/davistroy/claude-marketplace

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 validate-plugin.eval

README.md
[![agentmods](https://agentmods.dev/badge/commands/davistroy/claude-marketplace/validate-plugin.eval.svg)](https://agentmods.dev/commands/davistroy/claude-marketplace/validate-plugin.eval)
Your own site
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/validate-plugin.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/validate-plugin.eval.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 679 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 5.1 $0.00000 $0.00679
Opus 5 $0.00000 $0.00340
Sonnet 5 $0.00000 $0.00136
Haiku 4.5 $0.00000 $0.00068

Measured 5d ago against content hash 9d784e1ba210, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

validate-plugin.eval 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 5d 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.

evals/commands/validate-plugin.eval.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval: /validate-plugin

Purpose

Validates a plugin's directory structure, frontmatter fields, and content for consistency and correctness. Good output: a clear pass/fail result with specific findings for any structural or metadata issues.

Fixtures

None — operates on plugins in the marketplace repo.

Test Scenarios

S1: Validate personal-plugin (should pass)

Invocation: /validate-plugin personal-plugin

Must:

  • Checks plugins/personal-plugin/.claude-plugin/plugin.json exists and is valid JSON
  • Checks all commands/*.md files have valid frontmatter (description field, no name field)
  • Checks all skills/*/SKILL.md files have name and description in frontmatter
  • Reports overall PASS or FAIL
  • No false positives on a known-good plugin

Should:

  • Reports count of commands and skills validated
  • Lists any warnings (non-fatal issues)

Must NOT:

  • Report FAIL for a plugin that is structurally correct

S2: Validate bpmn-plugin

Invocation: /validate-plugin bpmn-plugin

Must:

  • Passes without false positives on the bpmn-plugin structure

S3: Validate --all plugins

Invocation: /validate-plugin --all

Must:

  • Validates every plugin registered in marketplace.json
  • Reports pass/fail for each
  • Reports any naming collisions (two plugins with the same command name)

S4: Detect missing name in skill frontmatter

Setup: Temporarily create a test skill file with no name field:

mkdir -p plugins/personal-plugin/skills/testbad
echo "---
description: test skill without name
---
# Test" > plugins/personal-plugin/skills/testbad/SKILL.md

Invocation: /validate-plugin personal-plugin

Must:

  • Reports FAIL with specific error: skill testbad is missing name field
  • References the exact file path

Cleanup: Remove the test skill after eval.


S5: Detect flat skill file (wrong structure)

Setup: Create plugins/personal-plugin/skills/flatskill.md (flat, not nested).

Read the full file on GitHub · 110 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. 5d ago First seen · 110 lines · 0 tokens per session scan A 9d784e1ba210

Subscribe to this mod's changes

validate-plugin.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 679 tokens. 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.