shell-shortcuts

shell-shortcuts is a skill for Claude Code, Codex from wangyendt/wayne-skills. It costs 76 tokens per session (2,154 once invoked), scanned A, original, MIT.

A set of terminal shortcuts for Windows, macOS, and Ubuntu, including proxy toggles, saved directory jumps, NVIDIA GPU status, and optional Conda environment activation. A terminal is the text-based program used to run system and development commands.

In plain words
What is it for?
Use it when configuring a new computer, switching proxy settings, jumping to frequently used folders, checking an NVIDIA GPU, or automatically activating a Conda environment.
Why use it?
It avoids repeatedly typing setup commands and helps keep a developer's shell behavior consistent across machines.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when configuring a new computer, switching proxy settings, jumping to frequently used folders, checking an NVIDIA GPU, or automatically activating a Conda environment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wangyendt/wayne-skills/shell-shortcuts
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 wangyendt/wayne-skills --skill shell-shortcuts
Clone the repo
git clone --depth 1 https://github.com/wangyendt/wayne-skills

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 shell-shortcuts

README.md
[![agentmods](https://agentmods.dev/badge/skills/wangyendt/wayne-skills/shell-shortcuts/github.svg)](https://agentmods.dev/skills/wangyendt/wayne-skills/shell-shortcuts)
Your own site
<a href="https://agentmods.dev/skills/wangyendt/wayne-skills/shell-shortcuts"><img src="https://agentmods.dev/badge/skills/wangyendt/wayne-skills/shell-shortcuts/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 shell-shortcuts

Your own site · 80×15
<a href="https://agentmods.dev/skills/wangyendt/wayne-skills/shell-shortcuts"><img src="https://agentmods.dev/badge/skills/wangyendt/wayne-skills/shell-shortcuts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,154 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00076 $0.02154
Opus 5.5 $0.00030 $0.00862
Sonnet 5.5 $0.00015 $0.00431
Haiku 4.5 $0.00008 $0.00215

Measured 2mo ago against content hash 02e3b91879bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shell-shortcuts 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 2mo 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.

shell-shortcuts/SKILL.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell Shortcuts (proxy_on, proxy_off, goto, gpu, conda autostart)

Goal: make a fresh machine behave the same across Windows / macOS / Ubuntu with a small set of commands:

  • proxy_on / proxy_off: toggle terminal proxy (env vars + Git global proxy)
  • goto: persistent path shortcuts (e.g. goto work)
  • gpu: show NVIDIA GPU status (nvidia-smi wrapper; Windows/Ubuntu only)
  • Optional: auto-activate a Conda env when a new shell starts

This skill is intentionally opinionated:

  • Prefer PowerShell on Windows for the full goto experience.
  • Keep everything idempotent by putting functions/scripts behind a clearly-marked block.

Defaults (edit as needed)

  • HTTP/HTTPS proxy: http://127.0.0.1:7890
  • SOCKS5 proxy: socks5://127.0.0.1:7890
  • NO_PROXY: localhost,127.0.0.1,.qualcomm.com,*.amazonaws.com

Edit your PowerShell profile: $PROFILE

Add (or replace) a block like below. The goto DB is $HOME\.goto_paths.json.

# >>> shell-shortcuts >>>

function proxy_off {
  param([switch]$Quiet)
  Remove-Item Env:http_proxy,Env:https_proxy,Env:all_proxy,Env:no_proxy -ErrorAction SilentlyContinue
  Remove-Item Env:HTTP_PROXY,Env:HTTPS_PROXY,Env:ALL_PROXY,Env:NO_PROXY -ErrorAction SilentlyContinue

  if (Get-Command git -ErrorAction SilentlyContinue) {
    git config --global --unset http.proxy 2>$null | Out-Null
    git config --global --unset https.proxy 2>$null | Out-Null
  }

  if (-not $Quiet) { Write-Host "Proxy is OFF" }
}

function proxy_on {
  param(
    [string]$HttpProxyUrl = "http://127.0.0.1:7890",
    [string]$SocksProxyUrl = "socks5://127.0.0.1:7890",
    [string]$NoProxyList = "localhost,127.0.0.1,.qualcomm.com,*.amazonaws.com"
  )

  proxy_off -Quiet

  $env:http_proxy  = $HttpProxyUrl
  $env:https_proxy = $HttpProxyUrl
  $env:HTTP_PROXY  = $HttpProxyUrl
  $env:HTTPS_PROXY = $HttpProxyUrl

  $env:all_proxy = $SocksProxyUrl
  $env:ALL_PROXY = $SocksProxyUrl

  $env:no_proxy = $NoProxyList
  $env:NO_PROXY = $NoProxyList

  if (Get-Command git -ErrorAction SilentlyContinue) {
    git config --global http.proxy  $HttpProxyUrl  | Out-Null
    git config --global https.proxy $HttpProxyUrl  | Out-Null
  }

  Write-Host "Proxy is ON"
  Write-Host "  HTTP/HTTPS: $HttpProxyUrl"
  Write-Host "  SOCKS5:     $SocksProxyUrl"
  Write-Host "  NO_PROXY:   $NoProxyList"
}

function _goto_db_path {
  Join-Path $HOME ".goto_paths.json"
}

function _goto_load {
  $db = _goto_db_path
  if (-not (Test-Path -LiteralPath $db)) { return @{} }
  try {
    $raw = Get-Content -Raw -Encoding UTF8 -LiteralPath $db
    if (-not $raw.Trim()) { return @{} }
    $obj = $raw | ConvertFrom-Json
    $ht = @{}
    foreach ($p in $obj.PSObject.Properties) { $ht[$p.Name] = [string]$p.Value }
    return $ht
  } catch {
    throw "Failed to parse goto DB: $db. Fix JSON or delete it."
  }
}

function _goto_save([hashtable]$ht) {
  $db = _goto_db_path
  $dir = Split-Path -Parent $db
  if (-not (Test-Path -LiteralPath $dir)) { New-Item -ItemType Directory -Path $dir | Out-Null }
  ($ht | ConvertTo-Json -Depth 5) | Set-Content -Encoding UTF8 -LiteralPath $db
}

function goto {
  param(
    [Parameter(Position = 0)][string]$Cmd,
    [Parameter(ValueFromRemainingArguments = $true)][string[]]$Rest
  )

  $ht = _goto_load

  switch ($Cmd) {
    { $_ -in @($null, "", "ls", "list") } {
      if ($ht.Count -eq 0) { Write-Host "No shortcuts. Use: goto add <key> <path>"; return }
      Write-Host "Available shortcuts:"
      foreach ($k in ($ht.Keys | Sort-Object)) {
        "{0,-12} -> {1}" -f $k, $ht[$k] | Write-Host
      }
      return
    }
    "add" {
      if ($Rest.Count -lt 2) { throw "Usage: goto add <shortcut> <path>" }
      $key = $Rest[0]
      $path = ($Rest | Select-Object -Skip 1) -join " "
      if ($path -like "~*") { $path = $path -replace "^~", $HOME }
      $resolved = Resolve-Path -LiteralPath $path -ErrorAction Stop
      $ht[$key] = $resolved.Path
      _goto_save $ht
      Write-Host "Added: $key -> $($ht[$key])"
      return
    }
    { $_ -in @("rm","remove","del") } {
      if ($Rest.Count -ne 1) { throw "Usage: goto remove <shortcut>" }
      $key = $Rest[0]
      $ht.Remove($key) | Out-Null
      _goto_save $ht
      Write-Host "Removed: $key"
      return
    }
    "clear" {
      _goto_save @{}
      Write-Host "All shortcuts cleared."
      return
    }
    default {
      if (-not $Cmd) { return }
      if (-not $ht.ContainsKey($Cmd)) {
        Write-Host "Unknown shortcut: $Cmd"
        Write-Host "Tip: goto list"
        return 1
      }
      Set-Location -LiteralPath $ht[$Cmd]
      return
    }
  }
}

function gpu {
  $cmd = Get-Command nvidia-smi -ErrorAction SilentlyContinue
  if (-not $cmd) {
    Write-Host "nvidia-smi not found (need NVIDIA driver/tools)."
    return 1
  }
  & $cmd.Path
}

# Optional: Conda auto-activate (edit these)
# $CondaRoot = "D:\\ProgramData\\miniconda3"
# $CondaEnv  = "wayne3.10"
# if (Test-Path -LiteralPath (Join-Path $CondaRoot "Scripts\\conda.exe")) {
#   $hook = (& (Join-Path $CondaRoot "Scripts\\conda.exe") "shell.powershell" "hook") 2>$null | Out-String
#   if ($hook) { Invoke-Expression $hook }
#   conda activate $CondaEnv
# }

# <<< shell-shortcuts <<<

Read the full file on GitHub · 238 lines

Files

What ships with it

2 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.

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. 2mo ago First seen · 238 lines · 76 tokens per session scan A 02e3b91879bf

Subscribe to this mod's changes

shell-shortcuts is a skill published in the GitHub repository wangyendt/wayne-skills (9 stars, last pushed 7d ago), licensed MIT. It adds 76 tokens to every session and 2,154 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

Cortex

LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…

danielmiessler/LifeOS · 184 tokens

rowboat-spaces

How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.

rowboatlabs/rowboat · 60 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens