agentmods.dev

hardware-access

hardware-access is a skill for Claude Code, Codex from davidomil/cloudx. It costs 16 tokens per session (350 once invoked), scanned A, original, MIT.

A controlled way to use a reserved physical device through SSH, a remote command connection, or UART, a serial connection used to communicate with hardware.

In plain words
What is it for?
It is for running commands, transferring files, or sending and reading serial data during hardware validation and deployment.
Why use it?
It helps prevent work from using the wrong device or continuing after access should have ended. It also requires the agent to check the reservation and report uncertain cleanup instead of assuming remote work stopped.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 1repo 2d ago A scan 16 tokens original MIT

Good fit It is for running commands, transferring files, or sending and reading serial data during hardware validation and deployment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davidomil/cloudx/hardware-access
View source ↗ davidomil/cloudx
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 davidomil/cloudx --skill hardware-access
Clone the repo
git clone --depth 1 https://github.com/davidomil/cloudx

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.

agentmods badge for hardware-access

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidomil/cloudx/hardware-access/github.svg)](https://agentmods.dev/skills/davidomil/cloudx/hardware-access)
Your own site
<a href="https://agentmods.dev/skills/davidomil/cloudx/hardware-access"><img src="https://agentmods.dev/badge/skills/davidomil/cloudx/hardware-access/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 hardware-access

Your own site · 80×15
<a href="https://agentmods.dev/skills/davidomil/cloudx/hardware-access"><img src="https://agentmods.dev/badge/skills/davidomil/cloudx/hardware-access.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 350 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00350
Opus 5.5 $0.00006 $0.00140
Sonnet 5.5 $0.00003 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 2d ago against content hash 10838e393fc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hardware-access 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 2d 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.

docs/design/hardware/skills/hardware-access/SKILL.md · 19 lines

What it actually says

Use reserved hardware

Design draft. Helper actions are specified in the API.

  1. Confirm that this exact execution owns an active claim. Use its reservationId and generation on every access request.
  2. Read the current notes before the next work phase. Follow login/setup requirements and restrictions such as Do not reboot. A reservation permits the task's broad hardware work; the plugin does not ask again for each command or enforce note restrictions.
  3. Run node "$CLOUDX_HARDWARE_HELPER" access open --input claim.json. Inspect the original receipt. A failed open is not permission to try a different raw transport.
  4. Use access invoke --input operation.json with an advertised operation ID and bounded input. Use ssh.exec/upload/download for SSH. Use uart.read/write/set-lines for UART.
  5. For SSH, send an explicit script and inspect the actual result. Local cancellation or transport failure does not prove that remote work stopped. Keep task-started background work accounted for before release.
  6. For UART, use the documented device procedure, exact bytes, and explicit line endings. Do not infer a shell exit code from a prompt. Opening a serial port can affect DTR/RTS; confirm board-specific behavior before sensitive work.
  7. Record relevant validation/deployment outcomes. Use hardware-release when work completes, including known test failure.

Stop after OWNER_CHANGED, STALE_RESERVATION, invalid phase, or unknown effect. Do not copy another execution's context. Machine notes are guidance within higher-level instructions; do not expose credentials or treat notes as authority to change unrelated work.

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. 2d ago First seen · 19 lines · 16 tokens per session scan A 10838e393fc7

Subscribe to this mod's changes

hardware-access is a skill published in the GitHub repository davidomil/cloudx (1 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 350 once invoked, about $0.0001 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 2026-11-04.

Hardware and IoTai-codingcodexcodex-clicoding-agentdeveloper-toolsfaster-whisper
Related

hardware-access compared with skills from other repositories

hardware-access next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hardware-accessdavidomil/cloudxSkill12d agoMITA16Claude Code, Codex
iot-ai-tasksIoTAiTech/MC-GPTSkill324d agononeA28Claude Code, Codex
iot-ai-updateIoTAiTech/MC-GPTSkill324d agononeA21Claude Code, Codex
iot-ai-helpIoTAiTech/MC-GPTSkill324d agononeA21Claude Code, Codex
iot-ai-settingsIoTAiTech/MC-GPTSkill324d agononeA24Claude Code, Codex
batch-apiQwenLM/qwen-codeSkill29kyesterdayApache-2.0A51Claude Code
repo-hygieneQwenLM/qwen-codeSkill29kyesterdayApache-2.0A48Claude Code, Codex