vdesign

vdesign is a skill for Claude Code from phamcuong21478/rtl-skills. It costs 17 tokens per session (4,777 once invoked), scanned A, original, Apache-2.0.

A hardware design tool that turns a Markdown requirement for a Verilog module into a proposed design, supporting documentation, and a starter RTL file. RTL is code that describes digital circuits.

In plain words
What is it for?
Use it for new submodules to create a function and architecture proposal, design documentation, and a Verilog skeleton ready for implementation.
Why use it?
It gives implementation a documented structure and a code backbone, reducing the need to start each module from a blank file.

Skill for Claude Code

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

Good fit Use it for new submodules to create a function and architecture proposal, design documentation, and a Verilog skeleton ready for implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/phamcuong21478/rtl-skills/vdesign
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 phamcuong21478/rtl-skills --skill vdesign
Clone the repo
git clone --depth 1 https://github.com/phamcuong21478/rtl-skills

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 vdesign

README.md
[![agentmods](https://agentmods.dev/badge/skills/phamcuong21478/rtl-skills/vdesign/github.svg)](https://agentmods.dev/skills/phamcuong21478/rtl-skills/vdesign)
Your own site
<a href="https://agentmods.dev/skills/phamcuong21478/rtl-skills/vdesign"><img src="https://agentmods.dev/badge/skills/phamcuong21478/rtl-skills/vdesign/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 vdesign

Your own site · 80×15
<a href="https://agentmods.dev/skills/phamcuong21478/rtl-skills/vdesign"><img src="https://agentmods.dev/badge/skills/phamcuong21478/rtl-skills/vdesign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,777 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 $0.00017 $0.04777
Opus 5 $0.00009 $0.02388
Sonnet 5 $0.00003 $0.00955
Haiku 4.5 $0.00002 $0.00478

Measured 12d ago against content hash f1bcf2003bbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vdesign 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.

skills/vdesign/SKILL.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verilog Designer

Overview

This guide defines the workflow for generating a design proposal, documentation, and a skeleton RTL module from a Markdown requirement file.

The input is a .md requirement file that describes what the module should do, typically ./ddoc/<module>_req.md produced by varch. The output is:

  1. A proposal file with function description, architecture and algorithm if applicable
  2. A design documentation file
  3. A backbone Verilog file with //@ direction comments, ready for implementation by vfill

vdesign runs once per new submodule. Reused lib modules have no _req.md (they are already designed and documented), so there is nothing here to drive — vdesign simply skips them; varch still instantiates them in the skeleton.

Module Name Derivation

All output file names are derived from the module name, not the raw requirement file name. The module name is the requirement file base name with any trailing _req removed.

Example:

  • requirement ./ddoc/foo_ctrl_req.md → module name foo_ctrl

Use this module name consistently for the proposal, documentation, and RTL backbone file names below.

Preconditions

Two stop conditions, checked before anything is written:

  • Requirement file missing. ./ddoc/<module>_req.md does not exist → stop and report: run varch first (or place a hand-written requirement file). Never design from a module name alone.
  • Target is the IP top. The module name resolves to <ip>_top → refuse. The top-level integration skeleton is owned by varch (it has no _req.md, and its //@ are integration notes, not fill directions); vdesign generates submodule backbones only.

Before You Start — Re-run Safety

vdesign overwrites three artifacts. Two of them carry hand-owned downstream content once the flow has progressed past vfill:

  • rtl/<module>.v — after vfill, this holds the real implementation and every //@ marker has been converted away. A blind re-generate destroys the implementation.
  • ddoc/<module>_proposal.mdvfill records design updates and debug notes in its ## Implementation Notes (vfill) section (seeded empty in Step 2). A blind re-generate clobbers them.

Read the full file on GitHub · 345 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 · 345 lines · 17 tokens per session scan A f1bcf2003bbb

Subscribe to this mod's changes

vdesign is a skill published in the GitHub repository phamcuong21478/rtl-skills (13 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 4,777 once invoked, about $0.0001 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.