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.
npx agentmods add instructions/netie-ai/openhbm/agents-mdgit clone --depth 1 https://github.com/Netie-AI/OpenHBMWrote 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.
[](https://agentmods.dev/instructions/netie-ai/openhbm/agents-md)<a href="https://agentmods.dev/instructions/netie-ai/openhbm/agents-md"><img src="https://agentmods.dev/badge/instructions/netie-ai/openhbm/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01169 | $0.01169 |
| Opus 5 | $0.00584 | $0.00584 |
| Sonnet 5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade C, and why
OpenHBM AGENTS.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 5d 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 How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the entry point for any AI coding agent (Claude, GPT, Gemini, or
otherwise) operating in this repository. It is the symlink-equivalent companion
to CLAUDE.md -- agents that look for AGENTS.md first should read both.
Read CLAUDE.md next. It contains the binding contract: SystemVerilog
subset, banned constructs, clock-domain rules, primitive library, CSR
generation rule, and the assertion-first workflow.
Operating principles
- Spec first, code second. Before writing any RTL, produce a port and parameter table, a cycle-by-cycle timing narrative, and SVA assertions for every protocol invariant. Then implement.
- Test-with against a Python golden reference. Every leaf IP gets a
dv/env/<ip>_ref.pymodel. Cocotb tests check RTL output against the reference, not against handwritten expected values. - Lint clean, formal clean, mutation-tested. A PR is not mergeable until
verible-verilog-lint,verilator -Wall --timing, the cocotb suite,sby(where applicable), andmcymutation coverage all pass the gate threshold (80/100 score; seetools/agent_eval/harness/scoring.py). - Hjson + reggen for every CSR. Never hand-write a CSR file.
- DCO on every commit.
git commit -s. No exceptions. - No JEDEC PDF redistribution. Spec summaries go in
docs/spec/, derived clean-room from the free-registration PDF held in a non-redistributable local cache. - No iEDA / OSCC code vendored into
hw/vendor/until export-controls counsel and license counsel both clear it. Seedocs/legal/export_control.md. Use iEDA via the prebuilt Docker image as a tool only.
Where to look
| You want to ... | Read |
|---|---|
| Understand the strategic plan | Plan.md |
| Understand the current execution sprint | .cursor/plans/openhbm4_*.plan.md |
| Find the binding RTL style contract | CLAUDE.md |
| Generate RTL for a specific IP | docs/agent-prompts/<ip>.md |
| Run the eval harness | tools/agent_eval/harness/run.py |
| Add a new IP | docs/rfcs/template.md |
| Vendor an external dependency | util/vendor.py + hw/vendor/*.lock.hjson |
| Run an ASIC flow | pd/sc_flows/<target>.py |
| Reproduce the toolchain | flake.nix or .devcontainer/devcontainer.json |
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.
- 5d ago First seen · 89 lines · 1,169 tokens per session scan C d8b17982a80f
OpenHBM AGENTS.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 1,169 tokens to every session, about $0.0058 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.
Other instructions, from other repositories
cml-mcp AGENTS.md
AGENTS.md instructions for xorrkaz/cml-mcp, covering agents.md — cml mcp server, project overview, compatibility goal, repository layout and tool modules (src/cmlmcp/tools/).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
cad-cae-copilot copilot-instructions.md
Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.