powershell-safe-vars

powershell-safe-vars is a skill for Codex from GalaxyRuler/Galactic-skills. It costs 48 tokens per session (2,881 once invoked), scanned A, original, MIT.

A set of rules for writing PowerShell commands and scripts with safe variable names, quoting, and paths. PowerShell is Microsoft's command shell and scripting language.

In plain words
What is it for?
Use it when creating or editing PowerShell commands, one-line scripts, shell tool calls, automations, or code that interpolates paths and strings.
Why use it?
It helps avoid failures caused by reserved automatic variables, case-insensitive names, and quoting rules that differ from Bash.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it when creating or editing PowerShell commands, one-line scripts, shell tool calls, automations, or code that interpolates paths and strings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/galaxyruler/galactic-skills/powershell-safe-vars
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 GalaxyRuler/Galactic-skills --skill powershell-safe-vars
Clone the repo
git clone --depth 1 https://github.com/GalaxyRuler/Galactic-skills

Made for: 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 powershell-safe-vars

README.md
[![agentmods](https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/powershell-safe-vars/github.svg)](https://agentmods.dev/skills/galaxyruler/galactic-skills/powershell-safe-vars)
Your own site
<a href="https://agentmods.dev/skills/galaxyruler/galactic-skills/powershell-safe-vars"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/powershell-safe-vars/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 powershell-safe-vars

Your own site · 80×15
<a href="https://agentmods.dev/skills/galaxyruler/galactic-skills/powershell-safe-vars"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/powershell-safe-vars.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,881 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 $0.00048 $0.02881
Opus 5.5 $0.00019 $0.01152
Sonnet 5.5 $0.00010 $0.00576
Haiku 4.5 $0.00005 $0.00288

Measured 2mo ago against content hash 8edc9836c290, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

powershell-safe-vars 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.

skills/powershell-safe-vars/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PowerShell: Safe Variables, Quoting, and One-Liners

When to use

Use this when writing or editing PowerShell (pwsh) commands/scripts inside Codex tool calls, especially for automations and one-liner scripts.

Problems this prevents

PowerShell has automatic variables (some are read-only / constant), and variable names are case-insensitive. Accidentally assigning to one of these (e.g. $HOME, $Host) can cause a script to fail with errors like “Cannot overwrite variable … because it is read-only or constant.”

PowerShell also parses quoting, pipes, redirection, and command substitution differently than Bash. Copying Bash snippets directly can produce ParserError, Missing file specification after redirection operator, The term 'from' is not recognized, or An empty pipe element is not allowed.

Workflow

  1. Pick “safe” variable names
  • Prefer descriptive names like $userHome, $codexHome, $installRoot, $sessionDir.
  • Avoid short/common names that collide with automatic variables, including:
    • $HOME (often constant) → use $userHome
    • $Host (automatic variable) → use $hostInfo / $hostProc
    • $PID, $PSVersionTable, $Error, $Matches, $Profile, $PSScriptRoot, $PSCommandPath
  • Remember: $home and $HOME are the same variable.
  1. If you must reuse a risky name, change it immediately
  • Rename the local variable to a safe name and update all references.
  1. Keep “tool-call scripts” failure-loud
  • Start scripts with: $ErrorActionPreference='Stop'
  • Set timeouts explicitly in the tool call (e.g. timeout_ms) for long operations.
  1. Avoid string-interpolation parsing traps
  • If a variable is immediately followed by :, PowerShell can treat it like a scoped variable reference and throw: “Variable reference is not valid. ':' was not followed by a valid variable name character.”
  • Fix by using one of:
    • "${var}:suffix" (brace the variable)
    • ("{0}:{1}" -f $var, $suffix) (format operator)
  1. Treat optional env vars as optional
  • Some environments won’t set expected variables like $env:CODEX_HOME.
  • Prefer defensive fallbacks, e.g.:
    • $codexHome = if ($env:CODEX_HOME) { $env:CODEX_HOME } else { Join-Path $env:USERPROFILE '.codex' }

Read the full file on GitHub · 175 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 Changed · +37 lines · +14 tokens per session 8edc9836c290
  2. 2mo ago First seen · 138 lines · 34 tokens per session scan A 6a194d3ca972

Subscribe to this mod's changes

powershell-safe-vars is a skill published in the GitHub repository GalaxyRuler/Galactic-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 2,881 once invoked, about $0.0002 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

powershell-safe-vars compared with skills from other repositories

powershell-safe-vars next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
powershell-safe-varsGalaxyRuler/Galactic-skillsSkill52mo agoMITA48Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code