macos-maintenance

macos-maintenance is a skill for Claude Code, Codex from pivoshenko/pivoshenko.ai. It costs 169 tokens per session (1,846 once invoked), scanned B, original, MIT.

A read-only macOS health check that reviews updates, storage, disk status, memory, battery, backups, indexing, crashes, uptime, and login items.

In plain words
What is it for?
Use it for periodic Mac maintenance, checking Time Machine recency, spotting memory pressure or swap use, reviewing startup load, and confirming disk health.
Why use it?
It gives one report showing what is healthy, what needs attention, and what action may help before any fixes are applied.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool.

Good fit Use it for periodic Mac maintenance, checking Time Machine recency, spotting memory pressure or swap use, reviewing startup load, and confirming disk health.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pivoshenko/pivoshenko.ai/macos-maintenance
Install

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.

Any agent
npx skills add pivoshenko/pivoshenko.ai --skill macos-maintenance
Clone the repo
git clone --depth 1 https://github.com/pivoshenko/pivoshenko.ai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for macos-maintenance

README.md
[![agentmods](https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/macos-maintenance/github.svg)](https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/macos-maintenance)
Your own site
<a href="https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/macos-maintenance"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/macos-maintenance/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.

agentmods 80×15 button for macos-maintenance

Your own site · 80×15
<a href="https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/macos-maintenance"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/macos-maintenance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 169 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,846 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00169 $0.01846
Opus 5 $0.00084 $0.00923
Sonnet 5 $0.00034 $0.00369
Haiku 4.5 $0.00017 $0.00185

Measured 4d ago against content hash 414d47fe268c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

macos-maintenance scanned grade B with 1 finding 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 4d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **OS updates**: `sudo softwareupdate -i -a` — sudo -> ask; may require restart, say which updates do.
skills/macos-maintenance/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

macOS Maintenance

Periodic once-over: sweep (read-only) -> report -> confirm -> apply -> verify. Optimization = real wins only: updates applied, reboot when due, indexing sane, startup load lean. No snake-oil (purge, blind cache wipes, repair-permissions theater). Storage/junk -> macos-cleanup, hand off.

Sweep (read-only)

Run all categories, every one shows up in the report — clean ones as "ok", never silently omitted. Warn up front: softwareupdate -l + diskutil verifyVolume take a minute+.

  1. Updatessoftwareupdate -l (slow); brew update >/dev/null && brew outdated (metadata-only refresh, ok in sweep); brew doctor (warnings only, most are noise — flag real ones).
  2. Disk healthdf -h / free %; diskutil info disk0 | grep -i smart -> must say Verified; diskutil verifyVolume / (read-only First Aid, live-volume ok); tmutil listlocalsnapshots / count (thinning is automatic — report only).
  3. Memory/CPUmemory_pressure (plain run prints summary); sysctl vm.swapusage — heavy swap + warning level -> note worst consumers via top -l 2 -o mem -n 5 -stats pid,command,cpu,mem.
  4. Batterypmset -g batt; system_profiler SPPowerDataType | grep -E 'Cycle Count|Condition|Maximum Capacity' -> Condition ≠ Normal or capacity <80% = attention.
  5. Backupstmutil destinationinfo (configured at all?); tmutil latestbackup (may need Full Disk Access -> fallback tmutil listbackups | tail -1). Last backup >7d = attention; not configured = say so once, user's call.
  6. Spotlightmdutil -s / (enabled? stuck "in progress"?); ps aux | grep -E 'mds_stores|mdworker' | grep -v grep CPU%. Optimization: big dev trees indexed -> suggest Spotlight Privacy exclusions for build-artifact dirs (node_modules, target, .venv parents) — GUI only, System Settings -> Siri & Spotlight.
  7. Crashes/panicsls -lt ~/Library/Logs/DiagnosticReports | head; ls /Library/Logs/DiagnosticReports 2>/dev/null | grep -i panic. Repeated crashes of one app or any kernel panic = attention + name it.
  8. Uptimeuptime. >14d -> recommend reboot (memory leaks + pending updates accumulate; that's the whole fix, no theater).
  9. Startup loadosascript -e 'tell app "System Events" to get name of every login item' + LaunchAgents count. Just the headcount here — deep dead-agent audit lives in macos-cleanup, point there if list looks bloated.

Read the full file on GitHub · 56 lines

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.

  1. 4d ago Changed 414d47fe268c
  2. 9d ago First seen · 56 lines · 169 tokens per session scan B 729cbff57a42

Subscribe to this mod's changes

macos-maintenance is a skill published in the GitHub repository pivoshenko/pivoshenko.ai (4 stars, last pushed 4d ago), licensed MIT. It adds 169 tokens to every session and 1,846 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

newsjack-detector

Monitor current news and reaction signals, then decide which are credible newsjacking opportunities for a client. Uses the local monitoring engine for evidence, but the skill owns PR judgment, brand safety, standing, decay, angle fit, and handoff.

elvisun/newsjack · 54 tokens

crisis-holding

Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).

elvisun/newsjack · 67 tokens

find-journalists

Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.

elvisun/newsjack · 69 tokens

voice-extractor

Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…

elvisun/newsjack · 90 tokens

80-livekit-agents-majiayu000-claude-skill-registr

Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.

majiayu000/claude-skill-registry · 18 tokens

fact-check

Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the burden of proof on the…

elvisun/newsjack · 85 tokens