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-recoverygit 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-recovery)<a href="https://agentmods.dev/skills/rcarmo/piclaw-addons/linkr-recovery"><img src="https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/linkr-recovery/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-recovery"><img src="https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/linkr-recovery.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 | $0.00033 | $0.00584 |
| Opus 5.5 | $0.00013 | $0.00234 |
| Sonnet 5.5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
linkr-recovery 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linkr recovery
Use this skill for recovery and troubleshooting when a machine behind Linkr is not booting, not responding as expected, or appears to be in an ambiguous state.
Common cases
This skill covers:
- missed firmware-entry windows;
- boot loops;
- no-signal or black-screen reports;
- wrong keyboard layout or stuck modifiers;
- wrong boot target;
- missing install media;
- lost confidence in whether prior HID input delivered;
- unexpected firmware or recovery screens.
Recovery order
Prefer the least disruptive supported action first:
statussnapshot- read-only
capabilities - tiny corrective HID actions with preview first
input.releasefor suspected stuck key/button statereboot.planorfirmware.entry.planif a bounded retry is justified- operator-assisted physical intervention if tooling is insufficient
Do not jump straight to reset or power cycle.
Distinguish ambiguity sources
A black or static screen can mean different things:
- stale snapshot;
- resolution or mode change;
- monitor asleep but machine running;
- Linkr transport issue;
- attached machine off;
- firmware open at a display mode that looks different from expected.
Name the uncertainty instead of pretending the cause is known.
Unsafe recovery actions
Do not power-cycle during:
- firmware flashing;
- OS or package updates;
- disk encryption setup or recovery-key generation;
- filesystem repair;
- partition resize or migration.
Treat power.press, power.reset, power.cycle, media.mount, media.eject, and device.reboot as unavailable unless the selected profile has verified support.
Cancellation and uncertain delivery
job.cancelmay acknowledge cancellation before a running job has fully stopped.- A failed or interrupted HID send can leave input state uncertain.
- Observe first.
- Use
input.releaseonly for tracked uncertain state; it cannot undo already applied actions.
Firmware and bootloader repair
Bootloader repair, partition editing, Secure Boot or TPM changes, and password-reset work all require explicit scope. They are not implicit in a generic “please fix it” request.
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 · 88 lines · 33 tokens per session scan A b0979bb7af3a
linkr-recovery is a skill published in the GitHub repository rcarmo/piclaw-addons (23 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 584 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
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.