What is j6-ucp-hbm-infer?

A guide for writing Python code that connects a computer to BPU boards, specialized hardware used to run HBM model inference. It covers standard and flexible sessions over gRPC, a way for programs to communicate with remote services.

Use it to create single-model inference clients, share one inference server across processes, or run multi-model pipelines on a BPU board.

It removes the need to work out how to connect to the board, deploy model files over SSH, share board resources, and choose between session modes.

j6-ucp-hbm-infer — Skill for Claude Code and Codex by HorizonRobotics

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.

Any agent

npx skills add HorizonRobotics/OE-Skills --skill j6-ucp-hbm-infer

Clone the repo

git clone --depth 1 https://github.com/HorizonRobotics/OE-Skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-hbm-infer/github.svg)](https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-hbm-infer)

Your own site

<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-hbm-infer"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-hbm-infer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-hbm-infer"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-hbm-infer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,127 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.

Model	Per session	Once invoked
Fable 5.1	$0.00139	$0.03127
Opus 5.5	$0.00056	$0.01251
Sonnet 5.5	$0.00028	$0.00625
Haiku 4.5	$0.00014	$0.00313

Measured 2mo ago against content hash b33d0e379f30, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

j6-ucp-hbm-infer 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 2mo 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.

horizon/skills/ucp/j6-ucp-hbm-infer/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hbm_infer X86 Python Client Code Generation

Generate production-ready X86-side Python client code for hbm_infer — the Python SDK that connects to a BPU board via gRPC, deploys HBM models over SSH, runs inference, and manages board resources.

Quick Decision: Which Mode?

Scenario	Mode	Module
Single model, single process	Standard	`hbm_infer.hbm_rpc_session`
Multi-process inference sharing one server	Flexible	`hbm_infer.hbm_rpc_session_flexible`
Multi-model pipeline with shared board resources	Flexible	`hbm_infer.hbm_rpc_session_flexible`

Standard Mode — Quick Reference

from hbm_infer.hbm_rpc_session import HbmRpcSession

session = HbmRpcSession(
    host="<board_ip>",
    local_hbm_path="<hbm_file_path>",
)
# Use session, then always close
session.close_server()

HbmRpcSession.init parameters:

Parameter	Type	Default	Description
`host`	`str`	required	Board IP address
`local_hbm_path`	`Union[str, List[str]]`	required	Local HBM file path(s)
`username`	`str`	`"root"`	Board SSH username
`password`	`Optional[str]`	`None`	Board SSH password
`ssh_port`	`int`	`22`	SSH port
`remote_root`	`str`	`"/map/hbm_infer/"`	Board-side temp directory
`frame_timeout`	`int`	`90`	gRPC per-frame timeout (seconds)
`server_timeout`	`int`	`5`	Server auto-shutdown timeout (minutes)
`with_profile`	`bool`	`False`	Enable per-stage timing stats
`debug`	`bool`	`False`	Debug mode with extra logging
`compress_option`	`str`	`"NONE"`	gRPC compression: `"NONE"`, `"IN"`, `"INOUT"`
`core_id`	`Union[int, List[int]]`	`-1`	BPU core ID(s), -1=CORE_ANY
`remote_environment`	`Dict[str, Any]`	`{}`	Board-side environment variables

Key methods:

session(data, output_config=None, model_name=None) — Run inference
session.get_model_names() → List[str]
session.get_input_info(model_name=None) → Dict[str, Dict]
session.get_output_info(model_name=None) → Dict[str, Dict]
session.show_input_output_info(model_name=None) — Print model I/O info
session.get_profile(model_name=None) → Cumulative timing stats (avg/min/max in ms)
session.get_profile_last_frame(model_name=None) → Last-frame timing stats (ms)
session.close_server() — Must call explicitly to release board resources

Read the full file on GitHub · 229 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 229 lines · 139 tokens per session scan A b33d0e379f30

Subscribe to this mod's changes

j6-ucp-hbm-infer is a skill published in the GitHub repository HorizonRobotics/OE-Skills (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 139 tokens to every session and 3,127 once invoked, about $0.0006 per session on Opus 5.5. 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.

Data and AI Hardware and IoT

j6-ucp-hbm-infer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
j6-ucp-hbm-inferHorizonRobotics/OE-Skills	Skill	27	4mo ago	Apache-2.0	A	139	Claude Code, Codex
spark-environment-setupwshobson/agents	Skill	42k	yesterday	MIT	A	76	Claude Code
spark-memory-thermal-opswshobson/agents	Skill	42k	yesterday	MIT	A	59	Claude Code
spark-training-gotchaswshobson/agents	Skill	42k	yesterday	MIT	A	63	Claude Code
inference-serving-llama-cppdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	80	Claude Code, Codex
amc-run-rtsp-calibrationNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	59	Claude Code, Codex
deepstream-generate-pipelineNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	108	Claude Code