RTLDesignSherpa: Skill for Claude Code

.claude/skills/rds-dv-bfms/SKILL.md

rds-dv-bfms is a skill for Claude Code from sean-galloway/RTLDesignSherpa. It costs 100 tokens per session (656 once invoked), scanned A, original, MIT.

A guide to reusable bus functional models, or BFMs: components that drive, monitor, or decode hardware interface signals. It covers the RDS-DV framework's factories and components for interfaces such as AXI4, APB, AXIS, FIFO, and UART.

In plain words
What is it for?
Use it when building verification testbenches for GAXI, AXI4, AXI-Lite, APB, AXI-Stream, FIFO, DFI, UART, SMBus, and arbiter interfaces.
Why use it?
It avoids hand-building interface drivers and monitors and documents common setup mistakes. It also clarifies that choosing a BFM does not by itself make a test thorough.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is sean-galloway/RTLDesignSherpa's own configuration. It tells Claude Code how to work on RTLDesignSherpa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RTLDesignSherpa configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sean-galloway/RTLDesignSherpa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sean-galloway/RTLDesignSherpa/main/.claude/skills/rds-dv-bfms/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sean-galloway/RTLDesignSherpa

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 rds-dv-bfms

README.md
[![agentmods](https://agentmods.dev/badge/skills/sean-galloway/rtldesignsherpa/rds-dv-bfms/github.svg)](https://agentmods.dev/skills/sean-galloway/rtldesignsherpa/rds-dv-bfms)
Your own site
<a href="https://agentmods.dev/skills/sean-galloway/rtldesignsherpa/rds-dv-bfms"><img src="https://agentmods.dev/badge/skills/sean-galloway/rtldesignsherpa/rds-dv-bfms/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 rds-dv-bfms

Your own site · 80×15
<a href="https://agentmods.dev/skills/sean-galloway/rtldesignsherpa/rds-dv-bfms"><img src="https://agentmods.dev/badge/skills/sean-galloway/rtldesignsherpa/rds-dv-bfms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 656 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00100 $0.00656
Opus 5 $0.00050 $0.00328
Sonnet 5 $0.00020 $0.00131
Haiku 4.5 $0.00010 $0.00066

Measured yesterday against content hash 3df0ef5965e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

rds-dv-bfms 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 yesterday.

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/rds-dv-bfms/SKILL.md · 41 lines

What it actually says

rds-dv-bfms

READ FIRST: vault/handbook/dv/bfm-usage.md (the handbook is the repo's memory; this skill is the signpost). Never hand-roll a driver/monitor/decoder; the note has the factory map and the trap list (falsy-BFM, signal_map keys, ready-delay windows).

Factories per family: gaxi_factories, axi4_factories, axil4_factories, apb_factories, axis_factories, fifo_factories. DFI/UART/SMBus have no factory module - construct components directly. Arbiters: ArbiterMaster + RoundRobinArbiterMonitor (components.shared); saturate with force_client_request(), never by poking dut.request - the master owns it.

ONE OF THREE ORTHOGONAL AXES (see rds-dv-axes): BFM = who drives; SEQUENCE = what traffic (rds-dv-axes); RANDOMIZATION = what timing (rds-dv-randomization). Using the right BFM says NOTHING about whether the test stresses anything.

Per-family API docs ship in RDS-DV under /docs/components// (published at sean-galloway.github.io/RTLDesignSherpa-DV). Read them rather than reverse-engineering from source -- but check what is actually there first, because coverage is uneven (measured 2026-09-10):

  • components_<family>_interfaces.md exists for axi4, axi5 and axil4 ONLY. This skill used to name that path for every family; for the other eight it points at nothing, which sends you to the source it is telling you to avoid.
  • A *_factories.md page exists for gaxi ONLY, though 11 families ship a factories module. The factories arrived after the docs were written.
  • Coverage of the rest varies and axil5 has NO pages at all. gaxi and fifo are the fullest; apb5, axis5 and wb4 have overview/components/packet; ls <RDS-DV>/docs/components/<family>/ before you rely on any of it.

Gap tracked as RDS-DV issue #78; until it closes, the components page plus the factory docstrings are the honest source for the undocumented families.

The handbook root is vault/handbook/INDEX.md - design/, dv/, fpga/, authoring/ areas, atomic notes, wikilinked. When you learn a durable lesson in this domain, ADD IT TO THE HANDBOOK NOTE, not to this skill.

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. yesterday Changed · +12 lines 3df0ef5965e4
  2. 12d ago First seen · 29 lines · 100 tokens per session scan A 1c6f7a239c6d

Subscribe to this mod's changes

rds-dv-bfms is a skill published in the GitHub repository sean-galloway/RTLDesignSherpa (23 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 656 once invoked, about $0.0005 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.