reference-driven-rohd

reference-driven-rohd is a skill for Claude Code, Codex from Midstall/claude-for-hardware. It costs 49 tokens per session (1,278 once invoked), scanned A, original, Apache-2.0.

A reference-based method for implementing hardware blocks, protocols, peripherals, or instruction-set features in ROHD, a hardware-description framework.

In plain words
What is it for?
It helps build components that must follow a datasheet, RFC, bus or peripheral standard, CRC or ECC definition, or instruction-set specification.
Why use it?
Specifications and existing implementations reveal reserved fields, edge cases, and exact behaviour that are easy to miss when writing from memory.

Skill for Claude CodeCodex

Part of the claude-for-hardware plugin — 14 skills, 3 commands, 3 agents, 1 hook shipped together

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.

agentmods
npx agentmods add skills/midstall/claude-for-hardware/reference-driven-rohd
Any agent
npx skills add Midstall/claude-for-hardware --skill reference-driven-rohd
Clone the repo
git clone --depth 1 https://github.com/Midstall/claude-for-hardware

Made for: Claude Code, Codex.

Or install claude-for-hardware, the plugin that ships this one along with the rest of its 14 skills, 3 commands, 3 agents, 1 hook.

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 reference-driven-rohd

README.md
[![agentmods](https://agentmods.dev/badge/skills/midstall/claude-for-hardware/reference-driven-rohd.svg)](https://agentmods.dev/skills/midstall/claude-for-hardware/reference-driven-rohd)
Your own site
<a href="https://agentmods.dev/skills/midstall/claude-for-hardware/reference-driven-rohd"><img src="https://agentmods.dev/badge/skills/midstall/claude-for-hardware/reference-driven-rohd.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,278 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00049 $0.01278
Opus 5 $0.00024 $0.00639
Sonnet 5 $0.00010 $0.00256
Haiku 4.5 $0.00005 $0.00128

Measured 4d ago against content hash 3d7bf24471f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reference-driven-rohd 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 4d 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/reference-driven-rohd/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reference-Driven ROHD

Overview

Writing a protocol or peripheral from memory is how you ship a design that is subtly wrong: a reserved bit in the wrong place, a handshake that almost matches the spec, an edge case the standard calls out that you never saw. The fix is cheap and boring: get the real sources first, then implement against them.

Core principle: Before writing custom ROHD, fetch the authoritative spec, the existing reference implementations, and any reusable library that already solves part of the problem. Implement from primary sources, not from recall. The spec is the oracle, the references show the behavior, the library saves the parts you should not rewrite.

When to Use

  • Implementing a standardized block (a bus, a UART, an SPI controller, a CRC, an ECC, a CSR file, an ISA extension)
  • Building something that must interoperate with hardware or software you do not control
  • You are about to write RTL from your own memory of how the protocol works
  • A datasheet, RFC, ISA manual, or vendor spec exists for what you are building

Skip for genuinely novel internal logic that has no external spec and no prior art.

Fetch The Sources First

Do this before writing a line of RTL. Three buckets, in order:

  1. The authoritative spec. The actual standard, datasheet, or ISA manual, not a blog summary. RISC-V unprivileged/privileged manuals, the Wishbone B4 spec, a part's datasheet PDF, the protocol's RFC. Use WebFetch/WebSearch to pull it, and note the exact version and section numbers. A spec you cite by section is a spec you can be held to.
  2. Existing reference implementations. Other HDL (Verilog/Chisel/SpinalHDL/migen), a C model, a vendor reference, an emulator. Clone or fetch them to read the behavior, especially the corner cases and reset values. These show you what the spec leaves ambiguous and how real implementations resolved it.
  3. Reusable libraries. Check rohd_hcl and existing Midstall ROHD (River, Harbor) before writing anything new. A FIFO, ECC, ready/valid handshake, rotator, or arbiter is probably already there, tested. Compose it; do not reinvent it.

Read the full file on GitHub · 75 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. 4d ago First seen · 75 lines · 49 tokens per session scan A 3d7bf24471f3

Subscribe to this mod's changes

reference-driven-rohd is a skill published in the GitHub repository Midstall/claude-for-hardware (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,278 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

integrated-browser

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.

microsoft/vscode · 68 tokens

import-prom-rule

Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…

ccfos/nightingale · 125 tokens

pcbway

PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…

aklofas/kicad-happy · 119 tokens

unifi-protect

How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person…

sirkirby/unifi-mcp · 112 tokens

tilelang-env-check

TileLang-Ascend 环境检查与配置验证技能。检查代码仓库完整性、编译安装状态、环境变量配置,并运行简单测试验证环境。发现问题会自动调用相关 skill 进行修复,并按依赖顺序重新执行后续步骤。触发关键词:"环境检查"、"检查环境"、"验证环境"、"环境配置"、"环境搭建"、"env check"、"check environment"、"verify environment"、"setup environment"。.

tile-ai/tilelang-ascend · 112 tokens

KernelWiki

Use when the user asks about optimizing NVIDIA Blackwell (SM100, B200) or Hopper (SM90, H100) GPU kernels — tcgen05/TMEM/CLC/NVFP4/2-SM cooperative, warp specialization, FlashAttention-4, DeepGEMM, FlashMLA, MoE, grouped GEMM, CuTe-DSL/PTX/Triton on Blackwell, or wants concrete PR references from…

mit-han-lab/KernelWiki · 143 tokens