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 skills add rcarmo/piclaw-addons --skill linkr-qualify-devicegit clone --depth 1 https://github.com/rcarmo/piclaw-addonsWrote 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/skills/rcarmo/piclaw-addons/linkr-qualify-device)<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.
<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>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 | $0.00039 | $0.00675 |
| Opus 5.5 | $0.00016 | $0.00270 |
| Sonnet 5.5 | $0.00008 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00068 |
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.
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:
idlabelorigintokenKeychaintargetIdentityinputEnabled
If targetIdentity is vague or clearly stale, update the operational record before relying on the profile.
Read-only first
Start with:
profile.listprofile.selectstatuscapabilitiessnapshot
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.planfirmware.entry.planjob.startwith ajobpayload 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.
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.
- 1mo ago First seen · 112 lines · 39 tokens per session scan A 68e1a02a86c4
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.
Other skills, from other repositories
cvm-ai-doctor
A health-diagnosis workflow for servers, computers, virtual machines, and containers on Linux, macOS, or Windows.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
investigate
Investigate a specific issue report with strict, evidence-driven diagnosis.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.