A test command that runs acceptance scenarios for the wicked-garden plugin and can also validate its skills. Acceptance tests check whether a feature works as expected from a user’s point of view.

Use it to validate skills, run one scenario, test every scenario in a domain, or test all available scenarios.

It provides a repeatable way to check plugin behavior across selected domains or scenarios.

wg-test — Command for Claude Code by mikeparcewski

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/mikeparcewski/wicked-garden/wg-test/github.svg)](https://agentmods.dev/commands/mikeparcewski/wicked-garden/wg-test)

Your own site

<a href="https://agentmods.dev/commands/mikeparcewski/wicked-garden/wg-test"><img src="https://agentmods.dev/badge/commands/mikeparcewski/wicked-garden/wg-test/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/mikeparcewski/wicked-garden/wg-test"><img src="https://agentmods.dev/badge/commands/mikeparcewski/wicked-garden/wg-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,910 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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.04910
Opus 5	$0.00006	$0.02455
Sonnet 5	$0.00003	$0.00982
Haiku 4.5	$0.00001	$0.00491

Measured 9d ago against content hash 7817a6466d44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wg-test 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 9d 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.

.claude/commands/wg-test.md · 500 lines

How it starts

The opening of the file, as written. The whole thing — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Scenarios

Dev-tool wrapper that delegates to the best available testing pipeline. QE owns acceptance testing end-to-end; the qe domain (E2E scenarios) provides standalone execution as a fallback. The --skills mode validates plugin skills against standards using the skill-creator skill.

Process

1. Parse Arguments

Parse $ARGUMENTS to determine what to test:

No args → Run skill validation (Step 7) THEN list domains with scenarios and ask user to pick
domain-name → Run skill validation for that domain (Step 7), then list scenarios for that domain and ask user to pick
domain/scenario-name → Run skill validation for that domain (Step 7), then run that specific scenario
domain --all → Run skill validation for that domain (Step 7), then run all scenarios for that domain
--all → Run skill validation for all domains (Step 7), then run all scenarios across all domains
--skills-only → Run ONLY skill validation (Step 7), skip scenarios entirely
--skills-only domain-name → Run ONLY skill validation for a specific domain
--no-skills → Skip skill validation, run scenarios only (legacy behavior)
--fix → During skill validation, auto-fix issues found
--issues flag (combinable with any above) → Auto-file GitHub issues for failures
--batch N → Run scenarios in batches of N in parallel (default: sequential)
--debug → Write debug log capturing tool-usage traces per batch

Execution order: Skill validation (Step 7) always runs first unless --no-skills is specified. Scenario execution (Steps 2-6) runs after, unless --skills-only is specified.

2. Preflight Environment Check

Before running any scenarios, verify the plugin runtime is available:

if [ "${SKIP_PLUGIN_MARKETPLACE}" = "true" ]; then
  echo "SKIP_PLUGIN_MARKETPLACE=true is set — plugin skills will not be registered."
  echo "Scenarios WILL FAIL because slash commands like /wicked-garden:mem:store cannot resolve."
  echo "Remove this env var or set SKIP_PLUGIN_MARKETPLACE=false to enable plugin loading."
fi

Read the full file on GitHub · 500 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.

9d ago First seen · 500 lines · 13 tokens per session scan A 7817a6466d44

Subscribe to this mod's changes

wg-test is a command published in the GitHub repository mikeparcewski/wicked-garden (9 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 4,910 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.

Testing

prototype

You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.

grainulation/grainulator · 0 tokens

verify

Run repository verification using the verification-loop skill.

cloudnative-co/claude-code-starter-kit · 9 tokens

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

wg-test