wg-scaffold

wg-scaffold is a command for Claude Code from mikeparcewski/wicked-garden. It costs 0 tokens per session (837 once invoked), scanned A, original, MIT.

A scaffolding command that creates the starting files and folders for a skill, agent, command, or hook in the wicked-garden plugin.

In plain words
What is it for?
Use it to start a named component in a chosen domain, then inspect the generated structure and continue by customizing, validating, and testing it.
Why use it?
It removes the repetitive setup work and helps new components follow the plugin’s expected structure.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .claude/skills/scaffolding/scripts/scaffold.py $ARGUMENTS.

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

Good fit Use it to start a named component in a chosen domain, then inspect the generated structure and continue by customizing, validating, and testing it.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mikeparcewski/wicked-garden
agentmods
npx agentmods add commands/mikeparcewski/wicked-garden/wg-scaffold

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-scaffold

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/mikeparcewski/wicked-garden/wg-scaffold"><img src="https://agentmods.dev/badge/commands/mikeparcewski/wicked-garden/wg-scaffold.svg" alt="Reviewed on agentmods" width="80" 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 837 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00837
Opus 5 $0.00000 $0.00418
Sonnet 5 $0.00000 $0.00167
Haiku 4.5 $0.00000 $0.00084

Measured 12d ago against content hash eedf9b085366, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

wg-scaffold 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 12d 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-scaffold.md · 126 lines

How it starts

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

Scaffold a new component within the unified wicked-garden plugin using the development tools.

Arguments

Parse the provided arguments: $ARGUMENTS

Expected format: [type] [name] --domain [domain] [description]

  • type: One of skill, agent, command, or hook
  • name: kebab-case name for the component
  • --domain: Target domain (e.g., crew, qe, engineering, mem)
  • description: Brief description (can be in quotes for multi-word)

If arguments are provided

Run the scaffold script:

python3 .claude/skills/scaffolding/scripts/scaffold.py $ARGUMENTS

After scaffolding:

  1. Show the created directory structure
  2. Explain what files were generated
  3. Suggest next steps (customize, validate, test)

If arguments are missing or incomplete

Enter interactive mode - ask the user:

  1. What type of component? (skill, agent, command, hook)
  2. Which domain? (crew, engineering, platform, qe, product, delivery, data, jam, mem, search, smaht, kanban, scenarios, patch, agentic, observability)
  3. What should it be named? (kebab-case)
  4. Brief description of purpose

Then run the scaffold with gathered information.

Component Types and Generated Paths

Skill

/wg-scaffold skill my-skill --domain crew "Brief description"

Creates:

skills/crew/my-skill/
├── SKILL.md          # ≤200 lines entry point
└── refs/             # Progressive disclosure (add as needed)

Agent

/wg-scaffold agent my-agent --domain platform "Brief description"

Creates:

agents/platform/my-agent.md    # Agent with frontmatter

Agent subagent_type: wicked-garden:platform:my-agent

Command

/wg-scaffold command my-command --domain engineering "Brief description"

Creates:

commands/engineering/my-command.md    # Command with YAML frontmatter

Command namespace: wicked-garden:engineering:my-command

Hook

/wg-scaffold hook my-hook --event PreToolUse "Brief description"

Creates:

hooks/scripts/my-hook.py    # Hook script (stdlib-only)

Updates hooks/hooks.json with the new event binding.

Read the full file on GitHub · 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. 12d ago First seen · 126 lines · 0 tokens per session scan A eedf9b085366

Subscribe to this mod's changes

wg-scaffold is a command published in the GitHub repository mikeparcewski/wicked-garden (9 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 837 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.