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 | $0.00181 | $0.02071 |
| Opus 5 | $0.00090 | $0.01035 |
| Sonnet 5 | $0.00036 | $0.00414 |
| Haiku 4.5 | $0.00018 | $0.00207 |
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 today.
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 — 163 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 (192.168.0.61), Portal (192.168.0.116), PostgreSQL (192.168.0.134) —
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.
The workflow
1. Check
Call ubuntu_check_updates on all three servers with refresh_cache: true. 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 three 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.
If nothing is pending anywhere, say so and stop — no need to touch the rest of this workflow or write a change doc for a no-op check.
2. Choose an execution strategy
Default: canary-then-parallel. Run the full install→verify sequence on Plex alone first (it has the lowest blast radius — a media server, not the production database). Once Plex comes back healthy, run Portal and PostgreSQL together in parallel. This means a bad update surfaces on one low-stakes box before it ever touches the other two.
Full parallel: only when Nic explicitly asks for speed ("in parallel", "minimize the time", "hit all three at once"). Say plainly that you're skipping the staged safety margin because he asked for it — don't do this silently. It's a reasonable trade for routine security patches (glibc, Python, kernel point releases) but worth naming out loud each time, since he may not want it for something riskier.
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.
- today 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 2d ago), licensed MIT. It adds 181 tokens to every session and 2,071 once invoked, about $0.0009 per session on Opus 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…
quick-capture
Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.
event-staffing-ordering
Order W-2 event staff for US/CA events through TempGuru.
delegacion-local
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…
chainstack
Work with the Chainstack MCP server to manage blockchain nodes and projects. Use when deploying nodes, migrating to Chainstack from another RPC provider such as QuickNode or Alchemy, checking platform status, searching Chainstack docs, contacting the Chainstack team, or interacting with the Chainstack platform API via…