linkr-qualify-device

linkr-qualify-device is a skill for Claude Code, Codex from rcarmo/piclaw-addons. It costs 39 tokens per session (675 once invoked), scanned A, original, MIT.

A qualification procedure for checking whether a Linkr profile and its attached computer are suitable for later remote automation. It starts with inventory and screenshots, then tests limited reversible input with evidence.

In plain words
What is it for?
Use it to verify machine identity, screenshot freshness, display details, keyboard assumptions, reversible input, firmware-entry keys, and unsupported functions.
Why use it?
A saved profile may point to the wrong machine or have incomplete capabilities. Checking the actual attached device prevents unsafe assumptions from being reused in BIOS work, installation, or recovery.

Skill for Claude CodeCodex

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

Good fit Use it to verify machine identity, screenshot freshness, display details, keyboard assumptions, reversible input, firmware-entry keys, and unsupported functions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rcarmo/piclaw-addons/linkr-qualify-device
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 rcarmo/piclaw-addons --skill linkr-qualify-device
Clone the repo
git clone --depth 1 https://github.com/rcarmo/piclaw-addons

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 linkr-qualify-device

README.md
[![agentmods](https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/linkr-qualify-device/github.svg)](https://agentmods.dev/skills/rcarmo/piclaw-addons/linkr-qualify-device)
Your own site
<a href="https://agentmods.dev/skills/rcarmo/piclaw-addons/linkr-qualify-device"><img src="https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/linkr-qualify-device/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 linkr-qualify-device

Your own site · 80×15
<a href="https://agentmods.dev/skills/rcarmo/piclaw-addons/linkr-qualify-device"><img src="https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/linkr-qualify-device.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 675 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 $0.00039 $0.00675
Opus 5.5 $0.00016 $0.00270
Sonnet 5.5 $0.00008 $0.00135
Haiku 4.5 $0.00004 $0.00068

Measured 1mo ago against content hash 68e1a02a86c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

linkr-qualify-device 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 1mo 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.

addons/linkr/skills/linkr-qualify-device/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Linkr qualify device

Use this skill before trusting a new Linkr profile for BIOS work, installation, or recovery.

Qualification is how you learn what is real for one machine without pretending the result is portable to every machine.

Required profile baseline

The profile should be configured in Settings with at least:

  • id
  • label
  • origin
  • tokenKeychain
  • targetIdentity
  • inputEnabled

If targetIdentity is vague or clearly stale, update the operational record before relying on the profile.

Read-only first

Start with:

  • profile.list
  • profile.select
  • status
  • capabilities
  • snapshot

Confirm the visible attached machine matches the intended profile. Qualification belongs to the machine actually on the cable, not just the Linkr appliance.

What to qualify

Qualify, with evidence:

  • screenshot freshness and resolution;
  • practical cadence for repeated snapshots;
  • keyboard layout assumptions;
  • simple reversible HID effects;
  • whether a documented firmware-entry key seems valid for this machine;
  • whether unsupported families remain unsupported in practice.

Reversible HID checks

Only with operator consent:

  • preview a tiny action first;
  • resend with execute:true;
  • verify with a new snapshot.

Good examples are moving focus one step in a visible menu or opening a harmless boot prompt. Do not begin with destructive actions.

Firmware timing qualification

Qualify firmware-entry timing only during a maintenance window. Use:

  • reboot.plan
  • firmware.entry.plan
  • job.start with a job payload like:
{
  "action": "job.start",
  "device_id": "lab-workstation-a",
  "job": {
    "kind": "firmware-entry",
    "duration_ms": 15000,
    "capture_interval_ms": 1000,
    "key": "F2",
    "key_evidence": "Vendor splash prompt and operator both say F2.",
    "tap_start_ms": 500,
    "tap_interval_ms": 250,
    "tap_duration_ms": 4000
  },
  "execute": true
}

Tie the resulting notes to the exact targetIdentity, visible firmware version when known, and date. A recipe learned on one firmware revision or one cable path may not survive hardware changes.

Read the full file on GitHub · 112 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. 1mo ago First seen · 112 lines · 39 tokens per session scan A 68e1a02a86c4

Subscribe to this mod's changes

linkr-qualify-device is a skill published in the GitHub repository rcarmo/piclaw-addons (23 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 675 once invoked, about $0.0002 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 2026-09-13.