windows-shell-commands

Shell-command guidance for Windows projects that use both PowerShell and Bash. It explains which shell to choose and how to pass quoted or multi-line text safely.

In plain words
What is it for?
Running Git and GitHub commands, writing commits or pull requests, handling multi-line text, and using POSIX tools or shell scripts when needed.
Why use it?
PowerShell and Bash use different command and quoting rules, so mixing their syntax can change commit messages, pull-request text, or file contents.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/srombauts/sqlitecpp/windows-shell-commands
Any agent
npx skills add SRombauts/SQLiteCpp --skill windows-shell-commands
Clone the repo
git clone --depth 1 https://github.com/SRombauts/SQLiteCpp

Made for: Claude Code, Codex.

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 801 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00095 $0.00801
Opus 5 $0.00048 $0.00400
Sonnet 5 $0.00019 $0.00160
Haiku 4.5 $0.00010 $0.00080

Measured 2d ago against content hash 7c5051c9da7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

windows-shell-commands scanned grade A 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Use the **Bash** tool for genuine POSIX work: `sed`/`awk` pipelines, `curl` one-liners, shell
.claude/skills/windows-shell-commands/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Windows Shell Commands

This repo is developed on Windows. Two shells are reachable from tools, and they do not share syntax. Mixing one shell's quoting into the other silently corrupts arguments.

Default to PowerShell

Prefer the PowerShell tool for shell commands on Windows, especially anything with quoting, multi-line text, or special characters (git commit, gh pr create, writing file content). It is the native shell here and its multi-line here-string works as documented.

Use the Bash tool for genuine POSIX work: sed/awk pipelines, curl one-liners, shell scripts, and .sh files. It runs Git Bash (POSIX sh), not cmd or PowerShell.

The trap: it is easy to type one shell's heredoc syntax into the other tool. The syntax below is not interchangeable.

Multi-line text: what works, what does not

Symptom of getting it wrong

A commit message or PR body comes out wrapped in literal characters, classically a lone @ line at the very top and bottom. That means a PowerShell here-string (@'...'@) was fed to the Bash tool, where @ is just a literal character concatenated onto the quoted string.

PowerShell tool (preferred)

Single-quoted here-string. The closing '@ MUST be at column 0 (no indentation) on its own line:

git commit -m @'
Subject line

Body paragraph with $literal dollar signs and "quotes" left intact.
'@

Use @'...'@ (literal, no expansion). Only use @"..."@ if you actually need $variable expansion. Indenting the closing '@ is a parse error.

Bash tool

A PowerShell here-string does NOT work here. Use one of these instead:

  • A real POSIX heredoc into git commit -F -:

    git commit -F - <<'EOF'
    Subject line
    
    Body paragraph.
    EOF
    
  • Multiple -m flags (each becomes a paragraph): git commit -m "Subject" -m "Body paragraph."

<<'EOF' (quoted delimiter) keeps the body literal; unquoted <<EOF expands $vars and backticks.

PR bodies and other long content: write a file

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 95 tokens per session scan A 7c5051c9da7a

Subscribe to this mod's changes

windows-shell-commands is a skill published in the GitHub repository SRombauts/SQLiteCpp (2,781 stars, last pushed 7d ago), licensed MIT. It adds 95 tokens to every session and 801 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

nemoclaw-contributor-implement-issue

Implement an accepted NemoClaw GitHub issue in the current checkout. Use when a user asks to pick up an issue for implementation, implement or fix a named issue, or add the issue's tests. Confirm accepted scope, deliver the smallest independently valuable capability slice, and record validation and remaining gates…

NVIDIA/NemoClaw · 134 tokens

amazon-bestseller-listing

Amazon Best Sellers listing scraper: extract product cards from any Amazon Best Sellers (zgbs) or /gp/bestsellers/ category page — returns rank (position on chart), asin, title, url, image, imageAlt, price, stars, reviewCount, ratingRaw per item, plus category metadata (categoryName, categoryFullName, categoryUrl) and…

browser-act/skills · 300 tokens

amazon-reviews-api-skill

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…

browser-act/skills · 124 tokens

amazon-competitor-analyzer

Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.

browser-act/skills · 48 tokens

cabloy-worktree-environment

This skill must be used only when the user explicitly invokes /cabloy-worktree-environment or explicitly asks to perform the named Cabloy worktree-environment setup. It prepares a confirmation-gated, worktree-local Vona and Zova runtime environment for a linked Cabloy Basic or Cabloy Start Git worktree using Git…

cabloy/cabloy · 126 tokens

shopify-hydrogen

Hydrogen storefront implementation cookbooks. Some of the available recipes are: B2B Commerce, Bundles, Combined Listings, Custom Cart Method, Dynamic Content with Metaobjects, Express Server, Google Tag Manager Integration, Infinite Scroll, Legacy Customer Account Flow, Markets, Partytown + Google Tag Manager…

Shopify/Shopify-AI-Toolkit · 106 tokens