design-first

design-first is a skill for Claude Code from valsecchi75/project-scaffolder. It costs 83 tokens per session (765 once invoked), scanned A, original, MIT.

A design checkpoint that guides decisions before implementation begins. It asks focused questions and compares a few approaches with their trade-offs before code is written.

In plain words
What is it for?
Use it before the first operational task in a project phase or for complex work, especially when requirements or technical choices need agreement.
Why use it?
It prevents important design choices from being made accidentally in the middle of implementation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

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

Good fit Use it before the first operational task in a project phase or for complex work, especially when requirements or technical choices need agreement.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/valsecchi75/project-scaffolder/design-first
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 valsecchi75/project-scaffolder --skill design-first
Clone the repo
git clone --depth 1 https://github.com/valsecchi75/project-scaffolder

Made for: Claude Code.

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 design-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/valsecchi75/project-scaffolder/design-first.svg)](https://agentmods.dev/skills/valsecchi75/project-scaffolder/design-first)
Your own site
<a href="https://agentmods.dev/skills/valsecchi75/project-scaffolder/design-first"><img src="https://agentmods.dev/badge/skills/valsecchi75/project-scaffolder/design-first.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 765 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 $0.00083 $0.00765
Opus 5 $0.00042 $0.00382
Sonnet 5 $0.00017 $0.00153
Haiku 4.5 $0.00008 $0.00076

Measured 8d ago against content hash e5114d251bde, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

design-first 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 8d 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.

skills/design-first/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design First — The Design Gate

Overview

Projects fail at execution when design questions surface mid-implementation. This skill forces the design conversation BEFORE the specialist writes code — and gives the approved design authority to revise decisions made at scaffold time, when knowledge was thinnest.

Core principle: the scaffold is an informed draft; the first operational design is where the rules truly settle.

When the gate triggers (called by Cortex Step 3b)

Condition Behavior
First operational task of the current phase MANDATORY
Complexity = Complex MANDATORY
Complexity = Medium Proposed — user may skip with --no-design
Trivial Skipped

The Design Dialogue

  1. Context read: CLAUDE.md (including Working Agreements), docs/phases/PHASE-{N}-execution.md, the design spec, relevant wiki pages. Never ask what these already answer.
  2. Questions — ONE at a time, max 5. Prefer multiple choice. Mode-aware: Normal asks all; Autopilot only the critical ones (irreversible choices, cost, genuinely missing requirements); Autonomous skips to step 3 and tags assumptions [HYPOTHESIS].
  3. 2-3 approaches with trade-offs and an explicit recommendation, recommended option first.
  4. Sectioned design: architecture of the change, data flow, error handling, verification plan. Ask after each section whether it looks right.
  5. Approval → write docs/design/TASK-{id}-design.md (compact, ≤80 lines) → execution proceeds with the design as the specialist's primary context.

Rule-Revision Authority (the key power)

The approved design MAY amend scaffold-era artifacts — with full traceability:

Artifact How
Execution Doc activities Add / split / re-scope activities; update token estimates
wiki/architecture.md, wiki/tech-stack.md Update affected sections; mark superseded content ~~strikethrough~~
wiki/product/decisions.md New DEC-NNN tagged [DESIGN-REVISION], citing the superseded DEC
Working Agreements (CLAUDE.md) Only with explicit user confirmation

Read the full file on GitHub · 59 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. 8d ago First seen · 59 lines · 83 tokens per session scan A e5114d251bde

Subscribe to this mod's changes

design-first is a skill published in the GitHub repository valsecchi75/project-scaffolder (9 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 765 once invoked, about $0.0004 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.

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens