vsynth

vsynth is a skill for Claude Code from phamcuong21478/rtl-skills. It costs 25 tokens per session (2,619 once invoked), scanned A, original, Apache-2.0.

A hardware design tool that uses Vivado to turn Verilog code into a circuit implementation and measure its resource use, speed, and power consumption.

In plain words
What is it for?
Use it to synthesize one Verilog module or a complete IP hierarchy, generate Vivado scripts, and produce utilization, timing, maximum-frequency, and power reports.
Why use it?
It replaces a manual synthesis-and-reporting process with a repeatable workflow. It also prevents unverified results when Vivado is unavailable.

Skill for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is # Design files (./rtl/) — always elaborated.

Good fit Use it to synthesize one Verilog module or a complete IP hierarchy, generate Vivado scripts, and produce utilization, timing, maximum-frequency, and power reports.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/phamcuong21478/rtl-skills
agentmods
npx agentmods add skills/phamcuong21478/rtl-skills/vsynth

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 vsynth

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/phamcuong21478/rtl-skills/vsynth"><img src="https://agentmods.dev/badge/skills/phamcuong21478/rtl-skills/vsynth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,619 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 $0.00025 $0.02619
Opus 5 $0.00013 $0.01309
Sonnet 5 $0.00005 $0.00524
Haiku 4.5 $0.00003 $0.00262

Measured 12d ago against content hash 56724dfb6f60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vsynth 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/vsynth/SKILL.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verilog Synthesizer

Overview

This guide defines the workflow for running Vivado out-of-context (OOC) synthesis on a single module or a full IP hierarchy and producing a structured synthesis report.

The input is a module or IP name. The outputs are:

  1. A Vivado TCL synthesis script in synth/<module>/
  2. Raw Vivado report files (utilization, timing, power)
  3. A structured synthesis report synth/<module>/synth_report.md

Prerequisites

Tool Purpose Check
Vivado Synthesis, optimization, and reporting vivado -version

Before running synthesis, verify Vivado is installed using the check command above. If it is missing, stop and report that Vivado is unavailable — never fabricate utilization, timing, power, or Fmax results. Steps 1–4 (scope, filelist, script generation) can still be done without the tool, but Steps 5–7 must not be reported as completed unless synthesis actually ran. (When invoked under vflow, this surfaces as ✗ BLOCKED (tool unavailable: vivado) for the Synthesis phase.)

Arguments

The skill takes a module or IP name. Optional overrides may follow as key=value pairs:

  • part=<vivado_part> — target device (default xczu7ev-ffvc1156-2-e)
  • period=<ns> — clock constraint period in ns (default 2.800)

Example: vsynth foo_top part=xc7a100t-csg324-1 period=5.0. When no overrides are given, use the defaults in Step 4.

Before You Start — Re-run Safety

Check whether synth/<module>/synth_report.md already exists:

State Detect Action
First run no synth/<module>/synth_report.md Generate the script and run synthesis normally.
Already synthesized report exists Do not silently re-synthesize. Re-run only if the user explicitly asks, an argument override changed (part/period), or an RTL source in the hierarchy is newer than the report (find <sources> -newer synth/<module>/synth_report.md). Otherwise report the existing result and stop. When you do re-run, overwrite the prior outputs in place rather than accumulating stale files.

Read the full file on GitHub · 287 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 · 287 lines · 25 tokens per session scan A 56724dfb6f60

Subscribe to this mod's changes

vsynth is a skill published in the GitHub repository phamcuong21478/rtl-skills (13 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 2,619 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.