scaffold

scaffold is a command for coding agents from valsecchi75/project-scaffolder. It costs 35 tokens per session (452 once invoked), scanned A, original, MIT.

A project-starting command that turns a short project brief into a structured workspace. It creates central instructions, a wiki, reusable task guidance, safety rules, and handoff files.

In plain words
What is it for?
Use it to start a new project in normal, autopilot, or autonomous mode, with the amount of questioning determined by the selected mode.
Why use it?
It gives an agent the shared project context and working structure needed for ongoing development.

Command

Part of the project-scaffolder plugin — 7 skills, 19 commands, 2 hooks shipped together

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/valsecchi75/project-scaffolder/scaffold
Clone the repo
git clone --depth 1 https://github.com/valsecchi75/project-scaffolder

Or install project-scaffolder, the plugin that ships this one along with the rest of its 7 skills, 19 commands, 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/commands/valsecchi75/project-scaffolder/scaffold.svg)](https://agentmods.dev/commands/valsecchi75/project-scaffolder/scaffold)
Your own site
<a href="https://agentmods.dev/commands/valsecchi75/project-scaffolder/scaffold"><img src="https://agentmods.dev/badge/commands/valsecchi75/project-scaffolder/scaffold.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 452 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 $0.00035 $0.00452
Opus 5 $0.00017 $0.00226
Sonnet 5 $0.00007 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured 5d ago against content hash 7cc90dd5250f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

commands/scaffold.md · 56 lines

What it actually says

/scaffold

Run the project-scaffolder skill to generate a complete project knowledge base from a user brief.

Usage

/scaffold [your project brief]
/scaffold --mode [normal|autopilot|autonomous] [your project brief]

Interaction Modes

Mode Flag Behavior
Normal --mode normal Asks all questions. Best for first-time users. (Default)
Autopilot --mode autopilot Asks only critical questions (~50% fewer). Makes reasonable defaults.
Autonomous --mode autonomous Zero questions. Makes all decisions independently. Maximum speed.

If no mode is specified, the scaffolder will ask you to choose.

Examples

/scaffold Mobile app for tracking gym workouts. Target: fitness enthusiasts. Flutter.
/scaffold --mode autopilot SaaS platform for restaurant reservations. React + Node. Target: Italian restaurant owners.
/scaffold --mode autonomous E-commerce site for handmade jewelry. Shopify + custom theme. Target: women 25-45.

What it generates

  1. CLAUDE.md — Central project hub read automatically by Claude Code
  2. Wiki (12 core pages + on-demand) — Karpathy-style persistent knowledge base
  3. Vertical skills — Domain-specific coding patterns, marketing guides, release gates
  4. Guardrails — Error prevention and anti-pattern documentation
  5. Design spec — Complete project specification
  6. Handoff — Session transition protocol for context preservation
  7. Daily log — Work tracking template

Extras

  • Interaction mode — Written into the generated CLAUDE.md so ALL future sessions respect your preferred level of autonomy

After scaffolding, start building with: claude → "Proceed with Phase 1"

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 · 56 lines · 35 tokens per session scan A 7cc90dd5250f

Subscribe to this mod's changes

scaffold is a command published in the GitHub repository valsecchi75/project-scaffolder (9 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 452 once invoked, about $0.0002 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.