claude-design-handoff

claude-design-handoff is a skill for Claude Code from rtazima/claude-proj-blueprint. It costs 69 tokens per session (1,652 once invoked), scanned A, original, MIT.

A workflow for reconciling a Claude Design handoff, a PROMPT.md file describing screens and design conventions, with a project's requirements and coding rules.

In plain words
What is it for?
Use it when a PRD references a Claude Design handoff or when a PROMPT.md file is present, so the intended screens, components, tokens, and interactions are checked against the project.
Why use it?
It resolves conflicts between business requirements, project conventions, visual design instructions, and generated code before implementation.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Good fit Use it when a PRD references a Claude Design handoff or when a PROMPT.md file is present, so the intended screens, components, tokens, and interactions are checked against the project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rtazima/claude-proj-blueprint/claude-design-handoff
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 rtazima/claude-proj-blueprint --skill claude-design-handoff
Clone the repo
git clone --depth 1 https://github.com/rtazima/claude-proj-blueprint

Made for: Claude Code.

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 claude-design-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/claude-design-handoff/github.svg)](https://agentmods.dev/skills/rtazima/claude-proj-blueprint/claude-design-handoff)
Your own site
<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/claude-design-handoff"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/claude-design-handoff/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 claude-design-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/claude-design-handoff"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/claude-design-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,652 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 $0.00069 $0.01652
Opus 5 $0.00034 $0.00826
Sonnet 5 $0.00014 $0.00330
Haiku 4.5 $0.00007 $0.00165

Measured 11d ago against content hash 5a29deafacb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claude-design-handoff 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 11d 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/skills/claude-design-handoff/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Design Handoff — PRD + PROMPT.md reconciliation

Claude Design is Anthropic Labs' design tool. The "Send to Claude Code" button produces a PROMPT.md bundle that describes: stack, conventions, screens to build, design tokens, and components. This skill reconciles that handoff with the project's PRD and CLAUDE.md conventions before code generation.

When this skill activates

  • /implement detects docs/design/<slug>-PROMPT.md next to the target PRD
  • PRD contains a reference like Design: docs/design/feat-x-PROMPT.md or a Claude Design URL
  • User explicitly mentions Claude Design, handoff bundle, or PROMPT.md

Source-of-truth hierarchy (conflict resolution)

When PRD, PROMPT.md, and CLAUDE.md disagree, precedence is strict:

  1. PRD (docs/product/*.md) — business contract. Wins on: scope, acceptance criteria, non-goals, metrics, personas.
  2. CLAUDE.md — project conventions. Wins on: language, framework, package manager, lint/format rules, commit style, folder structure.
  3. PROMPT.md (Claude Design) — visual/UX contract. Wins on: screens to build, components, design tokens, interaction patterns, copy.
  4. Generated code — last.

If PROMPT.md suggests a stack that contradicts CLAUDE.md, stop and ask the user. Do not silently adopt.

Workflow

  1. Locate the handoff bundle

    • Look for docs/design/<prd-slug>-PROMPT.md (same basename as PRD)
    • Fall back to any docs/design/*PROMPT.md mentioned in the PRD body
    • If none found, deactivate and let frontend-agent or Figma flow handle it
  2. Parse the handoff — extract, in order:

    • Stack hints (framework, component library, styling approach)
    • Design tokens (colors, typography, spacing, radii, shadows)
    • Screens list (names, routes, primary actions)
    • Components list (name + variants + states)
    • Copy and microcopy
    • Any "IMPORTANT" or "NEVER" directives from Claude Design
  3. Reconcile against CLAUDE.md

    • Compare stack hints to declared stack. Log each divergence.
    • Compare tokens to docs/specs/design-system/README.md. If empty, PROMPT.md becomes the seed. If filled, CLAUDE.md tokens win and PROMPT.md is treated as suggestion.
    • Compare component library to project's. If different, stop.

Read the full file on GitHub · 124 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. 11d ago First seen · 124 lines · 69 tokens per session scan A 5a29deafacb2

Subscribe to this mod's changes

claude-design-handoff is a skill published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 1,652 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.