Borrowing it
Nothing to install: this file belongs to PainInTheNic/MCP-Ubuntu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PainInTheNic/MCP-Ubuntu/main/.claude/skills/ubuntu-update-cycle/SKILL.mdgit clone --depth 1 https://github.com/PainInTheNic/MCP-UbuntuWrote 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/paininthenic/mcp-ubuntu/ubuntu-update-cycle)<a href="https://agentmods.dev/skills/paininthenic/mcp-ubuntu/ubuntu-update-cycle"><img src="https://agentmods.dev/badge/skills/paininthenic/mcp-ubuntu/ubuntu-update-cycle/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/paininthenic/mcp-ubuntu/ubuntu-update-cycle"><img src="https://agentmods.dev/badge/skills/paininthenic/mcp-ubuntu/ubuntu-update-cycle.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 | $0.00198 | $0.06241 |
| Opus 5.5 | $0.00079 | $0.02496 |
| Sonnet 5.5 | $0.00040 | $0.01248 |
| Haiku 4.5 | $0.00020 | $0.00624 |
Grade A, and why
ubuntu-update-cycle 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 16d 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 — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ubuntu update cycle
This encodes a workflow refined over many real update rounds on Nic's three home-lab
servers, including mistakes made and fixed along the way. The steps below aren't
arbitrary process for its own sake — each one exists because skipping it caused a real
problem at least once. Read references/lessons-learned.md if you want the war stories
behind a given step.
Servers: Plex (192.168.0.60), Portal (192.168.0.116), PostgreSQL (192.168.0.134) at
home, and Rex-PostgreSQL (100.93.156.59, tailnet IP) in the camper — full details,
roles, and per-host health checks in references/servers.md. Use
ubuntu_list_servers if you need to confirm the current inventory hasn't changed.
Rex-PostgreSQL is remote infrastructure. It's reached only over Tailscale on a cellular link, so it's slower and can drop out. It's part of every run of this cycle, the scheduled Sunday run included, unless Nic leaves it out. Every step that touches it follows the extra rules in Remote host: Rex-PostgreSQL below: longer waits, a detached install, deadlines, and toggling this Mac's Tailscale connection to get the link back. Below, "the home hosts" means Plex, Portal and PostgreSQL; "all four" adds Rex.
Never touch the Kitchen Sales Production VM (Nic's side-gig server). It runs its own automated updates and change-management docs. Even if it shows up in the inventory, skip it entirely and mention the skip in your report.
The workflow
1. Check
Call ubuntu_check_updates on all four servers with refresh_cache: true (Rex after
its link check). Nic's standing preference is a fresh apt-get update every time, not a
cached read — a stale cache can under-report what's actually pending. Checking is
read-only and safe to run in parallel on all four regardless of which install strategy
you use next.
If a check comes back with a refresh_warning (an apt lock held by a concurrent
process, e.g. unattended-upgrades running its own scan), don't trust that result —
retry once to get a clean read before deciding there's nothing to do.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 16d ago Changed · +7 lines 4df3e3b21152
- 17d ago Changed · +201 lines · +17 tokens per session 9c0bd43877bb
- 22d ago Changed · +4 lines c10a4ca7a553
- 25d ago Changed 26de05094706
- 1mo ago Changed · +8 lines ac55a5d0dc31
- 1mo ago Changed · +27 lines b5aaf752fa19
- 1mo ago First seen · 163 lines · 181 tokens per session scan A 4ca73cda368a
ubuntu-update-cycle is a skill published in the GitHub repository PainInTheNic/MCP-Ubuntu (0 stars, last pushed 16d ago), licensed MIT. It adds 198 tokens to every session and 6,241 once invoked, about $0.0008 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 2026-09-12.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.
quantum-fermi-hubbard-vqe
A variational quantum simulation of the open-boundary Fermi–Hubbard chain, a model of particles hopping between sites and interacting when they occupy the same system. It maps the model to qubits with the Jordan–Wigner transformation and searches for a low-energy state.
quantum-grover
A Qiskit implementation of Grover's algorithm, a quantum search method that increases the chance of finding a marked item. It can explain the method, build an explicit quantum circuit, or run it with chosen inputs.
quantum-algorithms
A routing workflow for choosing an open-source quantum-computing algorithm and loading the matching local workflow. Quantum computing uses circuits and quantum states to represent and process information.