wg-check

wg-check is a command for Claude Code from mikeparcewski/wicked-garden. It costs 11 tokens per session (11,442 once invoked), scanned A, original, MIT.

A quality-check command for the wicked-garden plugin, with quick structural checks and optional full marketplace assessment. A plugin is an add-on package for a coding agent.

In plain words
What is it for?
Use it to validate the plugin, review skills, assess agent trigger behavior, or run a full marketplace-readiness check.
Why use it?
It catches missing files, invalid configuration, and other readiness problems before release or during development.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool; positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the wicked-garden plugin — 148 skills, 5 commands, 1 agent, 13 hooks shipped together

Good fit Use it to validate the plugin, review skills, assess agent trigger behavior, or run a full marketplace-readiness check.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add mikeparcewski/wicked-garden
Claude Code
/plugin install wicked-garden

Made for: Claude Code.

Or install wicked-garden, the plugin that ships this one along with the rest of its 148 skills, 5 commands, 1 agent, 13 hooks.

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 wg-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/mikeparcewski/wicked-garden/wg-check/github.svg)](https://agentmods.dev/commands/mikeparcewski/wicked-garden/wg-check)
Your own site
<a href="https://agentmods.dev/commands/mikeparcewski/wicked-garden/wg-check"><img src="https://agentmods.dev/badge/commands/mikeparcewski/wicked-garden/wg-check/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 wg-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/mikeparcewski/wicked-garden/wg-check"><img src="https://agentmods.dev/badge/commands/mikeparcewski/wicked-garden/wg-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 11,442 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00011 $0.11442
Opus 5 $0.00005 $0.05721
Sonnet 5 $0.00002 $0.02288
Haiku 4.5 $0.00001 $0.01144

Measured 10d ago against content hash 743b660fe656, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wg-check scanned grade A 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 10d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

r = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
.claude/commands/wg-check.md · 1,126 lines

How it starts

The opening of the file, as written. The whole thing — 1,126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Check the wicked-garden plugin quality. Fast structural checks by default, full marketplace readiness with --full.

Arguments

Parse: $ARGUMENTS

  • --full: Run comprehensive assessment including product value evaluation
  • --agents: Run only the agent trigger frequency analysis (Section 10) in detail

The check always targets the repo root (the single unified plugin). No path argument needed.

If --agents is passed, skip all other sections and run only Section 10 (Agent Trigger Analysis) with detailed output.

Quick Check (Default)

Fast structural validation suitable for development iteration and CI.

Note: Bash snippets below use {path} as a template placeholder. Replace with the actual component path.

1. Plugin Structure

# Validate plugin.json exists and is valid
if [[ ! -f ".claude-plugin/plugin.json" ]]; then
  echo "ERROR: Missing .claude-plugin/plugin.json"
fi

# Validate version is semver (permits optional pre-release suffix like -beta.1)
version=$(jq -r '.version' ".claude-plugin/plugin.json")
if ! [[ "$version" =~ ^[0-9]+\.[0-9]+\.[0-9]+(-[A-Za-z0-9.-]+)?$ ]]; then
  echo "ERROR: Invalid semver version: $version"
fi

if ! python3 -m json.tool ".claude-plugin/plugin.json" > /dev/null 2>&1; then
  echo "ERROR: Invalid JSON in plugin.json"
fi

# (Phase 6c: the wicked_testing_version pin validation was removed — the
# wicked-testing peer retired; the qe domain ships in-catalog.) # historical

2. JSON Validity

for json_file in $(find "." -name "*.json" 2>/dev/null); do
  if ! python3 -m json.tool "$json_file" > /dev/null 2>&1; then
    echo "ERROR: Invalid JSON: $json_file"
  fi
done

3. Skill Line Counts

Skills MUST be ≤200 lines:

for skill in $(find "./skills" -name "SKILL.md" 2>/dev/null); do
  lines=$(wc -l < "$skill")
  name=$(dirname "$skill" | xargs basename)
  if [[ "$lines" -gt 200 ]]; then
    echo "ERROR: $name is $lines lines (max 200)"
  else
    echo "OK: $name ($lines lines)"
  fi
done

Read the full file on GitHub · 1,126 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. 10d ago First seen · 1,126 lines · 11 tokens per session scan A 743b660fe656

Subscribe to this mod's changes

wg-check is a command published in the GitHub repository mikeparcewski/wicked-garden (9 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 11,442 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.