scaffold

scaffold is a skill for Claude Code from ondrej-svec/heart-of-gold-toolkit. It costs 51 tokens per session (1,426 once invoked), scanned A, original, MIT.

A project-preparation workflow that creates folders, configuration, and development tools before coding begins. It deliberately does not create source-code or test files.

In plain words
What is it for?
Use it to read an architecture document, create the planned structure, write configuration files, install dependencies, and prepare tooling.
Why use it?
It prevents an empty project from being filled with premature placeholder code that can hide missing implementation. It also makes dependencies and project conventions ready for later work.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the marvin plugin — 13 skills, 3 agents, 2 hooks shipped together

Good fit Use it to read an architecture document, create the planned structure, write configuration files, install dependencies, and prepare tooling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ondrej-svec/heart-of-gold-toolkit/scaffold
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.

Any agent
npx skills add ondrej-svec/heart-of-gold-toolkit --skill scaffold
Clone the repo
git clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkit

Made for: Claude Code.

Or install marvin, the plugin that ships this one along with the rest of its 13 skills, 3 agents, 2 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 scaffold

README.md
[![agentmods](https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/scaffold/github.svg)](https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/scaffold)
Your own site
<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/scaffold"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/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 scaffold

Your own site · 80×15
<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/scaffold"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/scaffold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,426 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00051 $0.01426
Opus 5 $0.00026 $0.00713
Sonnet 5 $0.00010 $0.00285
Haiku 4.5 $0.00005 $0.00143

Measured 12d ago against content hash b805c7154227, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

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.

plugins/marvin/skills/scaffold/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scaffold

Prepare a project for development. Creates directories, configs, and installs dependencies — never source or test files.

Boundaries

This skill MAY: create directories, config files, install dependencies, set up tooling. This skill MAY NOT: create source files (*.ts, *.js, *.py, etc.), create test files, write implementation code, write test code.

NEVER create source or test files. Structure and configuration only.

Common Rationalizations

Shortcut Why It Fails The Cost
"Create a starter file — just a skeleton" Skeletons become the implementation. Test writers then test the skeleton, not real behavior Weak tests that pass with stubs
"Skip dependency install — implementer can do it" Missing deps cause confusing errors downstream Wasted time debugging missing imports
"Use default configs — they'll customize later" Default configs often conflict with project conventions Config drift → inconsistent behavior

Step 1: Read Architecture Doc

If $ARCH_PATH is set (pipeline mode):

  1. Read the architecture doc at $ARCH_PATH
  2. Extract: dependencies, file structure, external services
  3. Announce: "Reading architecture: [filename]."

If no env var (standalone mode):

  1. Use AskUserQuestion (header: "Project", question: "What project are you setting up? Provide an architecture doc path, or describe what you're building.")
  2. If they provide a path, read it
  3. If they describe it, gather: language/framework, dependencies, project type

Exit: Know what directories, dependencies, and configs are needed.


Step 2: Assess Project State

Determine if this is greenfield or brownfield:

# Check for existing project indicators
ls package.json pyproject.toml Cargo.toml go.mod 2>/dev/null
ls -d src/ lib/ app/ 2>/dev/null
  • Greenfield: No project manifest or source directories exist
  • Brownfield: Project exists — verify paths, note discrepancies with architecture doc

Read the full file on GitHub · 187 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 · 187 lines · 51 tokens per session scan A b805c7154227

Subscribe to this mod's changes

scaffold is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 51 tokens to every session and 1,426 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens