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-controlgit 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-control)<a href="https://agentmods.dev/skills/rcarmo/piclaw-addons/linkr-control"><img src="https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/linkr-control/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-control"><img src="https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/linkr-control.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 | $0.00036 | $0.01032 |
| Opus 5.5 | $0.00014 | $0.00413 |
| Sonnet 5.5 | $0.00007 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
linkr-control 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linkr control
Use this skill when Piclaw must interact with a specific machine through a Radxa Linkr KVM and safer direct methods such as SSH, guest agents, or browser automation are unavailable.
See tool contract and safety rules.
Start read-only
Before any input:
- Resolve the target with
profile.list,profile.select, andstatus. - Inspect
capabilitiesand note anyunsupportedfamilies. - Capture a fresh
snapshotand read both the image and metadata. - Confirm the visible screen matches the authorised task and
targetIdentity.
Do not infer authority from a selected profile alone.
Core operating loop
- Observe — take
snapshotand identify OS, active prompt, focus, and ambiguity. - Plan — choose the smallest next action that could safely advance the task.
- Preview — call the mutating action without
execute:truefirst when the next step is nontrivial. - Execute — resend with
execute:trueonly when the effect is authorised. - Verify — take a new
snapshotand confirm the result before continuing.
HTTP or API success only acknowledges delivery. It does not prove the remote application accepted the action.
Actions to prefer
For ordinary interactive control, prefer these actions and fields:
snapshotkey.tapwithdevice_id,keykey.combowithdevice_id,keyskey.repeatwithdevice_id,key,count,interval_mstextwithdevice_id,textmouse.movewithdevice_id,x,ymouse.clickwithdevice_id,x,ymouse.dragwithdevice_id,x,y,to_x,to_ymouse.scrollwithdevice_id,wheel_y,wheel_xinput.batchwithdevice_id,eventsinput.release
Use job.start only for bounded local capture or firmware-entry jobs, not as a generic macro recorder.
Exact examples
{"action":"key.tap","device_id":"lab-workstation-a","key":"Tab","execute":true}
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 · 117 lines · 36 tokens per session scan A 18d1f3f5b361
linkr-control is a skill published in the GitHub repository rcarmo/piclaw-addons (23 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,032 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 2026-09-13.
Other skills, from other repositories
profinet
PROFINET (L2 EtherType 0x8892 / DCP) attack playbook — DCP Identify-All broadcast enumeration, device fingerprinting, station-name and IP reassignment (breaks IO-controller mapping), flash-LED physical location, factory-reset, RT frame injection/replay for cyclic-IO spoofing. Siemens/EU fieldbus peer of S7Comm…
opentrons-integration
Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…
ics-overview
Use when the target is an industrial control system or operational technology network running Modbus, BACnet, S7Comm/S7Comm Plus, DNP3, OPC-UA, or any PLC/HMI/SCADA stack. Engagements MUST set RoE flag industrialsafetycritical=true; this catalog gates every write-scope operation behind explicit operator confirmation…
omh-physical-device-readiness
This is an OMH physical-device-readiness workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
x-smart
SMART disk health monitoring tool. Check disk health, temperature, and attributes using smartctl. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.