vfill

vfill is a skill for Claude Code from phamcuong21478/rtl-skills. It costs 17 tokens per session (2,680 once invoked), scanned A, original, Apache-2.0.

A workflow for implementing Verilog hardware code from an approved design proposal, then checking it with linting and simulation. Verilog is a language used to describe digital circuits; linting finds likely code and design problems before simulation.

In plain words
What is it for?
Use it to fill in a Verilog module, run Verilator or Xilinx checks when available, simulate the design, and report any missing tool or failed verification step.
Why use it?
Hardware changes must follow the approved design and depend on specialized tools that may not be installed. This workflow checks the source and tools first and does not claim tests passed when they did not run.

Skill for Claude Code

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

Good fit Use it to fill in a Verilog module, run Verilator or Xilinx checks when available, simulate the design, and report any missing tool or failed verification step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/phamcuong21478/rtl-skills/vfill
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 vfill
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 vfill

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/phamcuong21478/rtl-skills/vfill"><img src="https://agentmods.dev/badge/skills/phamcuong21478/rtl-skills/vfill.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 2,680 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 $0.02680
Opus 5 $0.00009 $0.01340
Sonnet 5 $0.00003 $0.00536
Haiku 4.5 $0.00002 $0.00268

Measured 11d ago against content hash 4024397ef63e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vfill 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.

skills/vfill/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verilog Writer

Overview

This guide defines the workflow for implementing a Verilog module from an approved design proposal.

Before starting, read:

  1. The target Verilog source file — for //@ annotations and port declarations
  2. The proposal file ./ddoc/<module_name>_proposal.md (same folder as the requirement file) — this is the source of truth for the implementation

Prerequisites

Tool Purpose Check
Verilator Verilog lint verilator --version
xvlog Xilinx Verilog compiler / lint xvlog --version
xelab Xilinx elaborator xelab --version
xsim Xilinx simulator xsim --version

Before running any lint or simulation step, verify the tool it needs is installed using the check command above. If a required tool is missing, stop and report which tool is unavailable — never fabricate lint, simulation, or elaboration results. The Verilog can still be filled in (Step 1) without the tools, but Steps 2 and 3 must not be reported as passed unless they actually ran. (When invoked under vflow, this surfaces as ✗ BLOCKED (tool unavailable: <tool>) for the dependent phase.)

Before You Start — Re-run Safety

Before editing, check rtl/<module>.v for //@ markers (the signal vflow uses for completion, CodingStyle §18):

State Detect Action
Backbone //@ markers present First run — implement, then convert every //@ away.
Already filled no //@ left / real logic present Filled before: do not re-fill from scratch. Make the requested change as an incremental edit, update the proposal's ## Implementation Notes (vfill) section in place rather than appending a duplicate, then re-lint and re-simulate.

Step 1 - Fill in the Verilog Code

Read the full file on GitHub · 222 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 · 222 lines · 17 tokens per session scan A 4024397ef63e

Subscribe to this mod's changes

vfill is a skill published in the GitHub repository phamcuong21478/rtl-skills (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 2,680 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.