OpenHBM: Instructions file for Claude Code

CLAUDE.md

OpenHBM CLAUDE.md is an instructions file for Claude Code from Netie-AI/OpenHBM. It costs 3,501 tokens per session, scanned C, original, Apache-2.0.

Binding repository instructions for OpenHBM's synthesizable SystemVerilog, a hardware-description language used to design circuits. They define the allowed language subset and coding rules that every hardware source file must follow.

In plain words
What is it for?
Use them when writing or reviewing OpenHBM hardware modules, especially sequential logic, combinational logic, state machines, assertions, and clock-crossing code.
Why use it?
They prevent RTL, or register-transfer-level hardware code, from using constructs that violate the project's synthesis and CI requirements.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is Netie-AI/OpenHBM's own configuration. It tells Claude Code how to work on OpenHBM 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 OpenHBM configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Netie-AI/OpenHBM. 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/Netie-AI/OpenHBM/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Netie-AI/OpenHBM

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 OpenHBM CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/netie-ai/openhbm/claude-md.svg)](https://agentmods.dev/instructions/netie-ai/openhbm/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/netie-ai/openhbm/claude-md"><img src="https://agentmods.dev/badge/instructions/netie-ai/openhbm/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,501 This file is loaded in full into every session.
When invoked 3,501 The same file — it is already loaded in full.
Security scan C 2 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 $0.03501 $0.03501
Opus 5 $0.01750 $0.01750
Sonnet 5 $0.00700 $0.00700
Haiku 4.5 $0.00350 $0.00350

Measured 8d ago against content hash b994377b31a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

OpenHBM CLAUDE.md scanned grade C with 2 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 8d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

The toolchain is already installed at `~/oss-cad-suite`. Never run any install script, `apt install`, `pip install`, `curl | bash`, or any package manager command to install EDA tools. If a tool is not found, the fix is

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

The toolchain is already installed at `~/oss-cad-suite`. Never run any install script, `apt install`, `pip install`, `curl | bash`, or any package manager command to install EDA tools. If a tool is not found, the fix is
CLAUDE.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md -- the binding RTL contract for Netie Open HBM

This file is read FIRST by every AI agent (Claude 4.7, GPT-5.5, Gemini 3.1, or any successor) before producing any code in this repository. Treat every section below as a hard requirement, not a guideline. Violations block CI.

If you also see AGENTS.md, read it second -- it indexes everything else.


1. SystemVerilog subset (synthesisable code)

The synthesisable subset is IEEE 1800-2017 with the following constraints:

1.1 Allowed

  • logic for all signals (no wire, no reg in synthesisable code).
  • always_ff @(posedge clk or negedge rst_ni) for sequential.
  • always_comb for combinational.
  • always_latch ONLY when justified by an inline comment explaining why a flop is not appropriate, and never on a clock-crossing path.
  • Packed structs and unions for bundled wires.
  • enum logic [...] for state encodings (one-hot or binary; specify in ()).
  • parameter and localparam for compile-time constants.
  • function automatic for combinational helpers.
  • Generate blocks with named labels (for (...) begin : g_name).
  • SVA properties via assert property, cover property, assume property.
  • import of an interface package into a leaf module IS allowed; declaring interface ports IS NOT (see 1.2).

1.2 Banned in synthesisable code

  • Four-state wire declarations (use logic).
  • reg keyword (use logic).
  • interface ports on leaf IP modules. (Top-level subsystem wrappers MAY use interfaces; leaf IP must use packed structs to keep tools portable.)
  • force / release.
  • disable fork.
  • event types.
  • class / virtual class (verification only).
  • mailbox, semaphore (verification only).
  • $random, $urandom, $urandom_range (use pyvsc constrained random in the testbench, never inside RTL).
  • Non-blocking assignment in always_comb (<= belongs only in always_ff).
  • Blocking assignment to a flop signal (= belongs only in always_comb).
  • Implicit nets. Set default_nettype none at every file top.
  • Synchronous-active-high resets (we use synchronous and asynchronous active-low rst_ni; see 3.2).
  • casex, casez (use case ... inside or unique case).
  • Bare case without unique or priority.
  • Multiple-driver nets.
  • Output-port driving from more than one always_* block.
  • defparam.
  • Behavioural delays (#5) outside testbenches.

Read the full file on GitHub · 344 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. 8d ago First seen · 344 lines · 3,501 tokens per session scan C b994377b31a2

Subscribe to this mod's changes

OpenHBM CLAUDE.md is an instructions file published in the GitHub repository Netie-AI/OpenHBM (24 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,501 tokens to every session, about $0.0175 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens