squad: Skill for Claude Code

.copilot/skills/windows-compatibility/SKILL.md

windows-compatibility is a skill for Claude Code, Codex from bradygaster/squad. It costs 12 tokens per session (1,572 once invoked), scanned A, original, MIT.

A set of coding rules for making file paths, timestamps, Git commands, and commit messages work across Windows, macOS, and Linux.

In plain words
What is it for?
It helps write cross-platform Node.js and Git workflows, locate the repository safely, create Windows-safe timestamps, and make commits from scripts.
Why use it?
It prevents bugs caused by differences between operating systems, such as invalid filenames, broken paths, and unreliable shell commands.

Skill for Claude CodeCodex

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

This is bradygaster/squad's own configuration. It tells Claude Code and Codex how to work on squad itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything squad configures →

About the project

bradygaster/squad is a tool that creates a human-directed team of AI development agents inside a project repository through GitHub Copilot. Developers use it to delegate work among persistent specialists such as frontend, backend, testing, and lead agents while retaining responsibility for decisions and review. The catalogue entries are the skills, agents, and instructions that define and coordinate those team members.

bradygaster/squad · 3,295 stars · on GitHub · bradygaster.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to bradygaster/squad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bradygaster/squad/dev/.copilot/skills/windows-compatibility/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bradygaster/squad

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 windows-compatibility

README.md
[![agentmods](https://agentmods.dev/badge/skills/bradygaster/squad/windows-compatibility/github.svg)](https://agentmods.dev/skills/bradygaster/squad/windows-compatibility)
Your own site
<a href="https://agentmods.dev/skills/bradygaster/squad/windows-compatibility"><img src="https://agentmods.dev/badge/skills/bradygaster/squad/windows-compatibility/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 windows-compatibility

Your own site · 80×15
<a href="https://agentmods.dev/skills/bradygaster/squad/windows-compatibility"><img src="https://agentmods.dev/badge/skills/bradygaster/squad/windows-compatibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,572 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00012 $0.01572
Opus 5.5 $0.00005 $0.00629
Sonnet 5.5 $0.00002 $0.00314
Haiku 4.5 $0.00001 $0.00157

Measured 1mo ago against content hash 88bdd5d8d5b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

windows-compatibility 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 1mo 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.

Origin

Copies of this mod

5 near-identical copies found in the catalogue:

.copilot/skills/windows-compatibility/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

Squad runs on Windows, macOS, and Linux. Several bugs have been traced to platform-specific assumptions: ISO timestamps with colons (illegal on Windows), git -C with Windows paths (unreliable), forward-slash paths in Node.js on Windows.

Patterns

Filenames & Timestamps

  • Never use colons in filenames: ISO 8601 format 2026-03-15T05:30:00Z is illegal on Windows
  • Use safeTimestamp() utility: Replaces colons with hyphens → 2026-03-15T05-30-00Z
  • Centralize formatting: Don't inline .toISOString().replace(/:/g, '-') — use the utility

Git Commands

  • Never use git -C {path}: Unreliable with Windows paths (backslashes, spaces, drive letters)
  • Always cd first: Change directory, then run git commands
  • Check for changes before commit: git diff --cached --quiet (exit 0 = no changes)

Commit Messages

  • Never embed newlines in -m flag: Backtick-n (\n) fails silently in PowerShell
  • Use temp file + -F flag: Write message to file, commit with git commit -F $msgFile

Paths

  • Never assume CWD is repo root: Always use TEAM ROOT from spawn prompt or run git rev-parse --show-toplevel
  • Use path.join() or path.resolve(): Don't manually concatenate with / or \

Path Comparison (Case Sensitivity)

  • Never use naive prefix checks to confine paths: a bare substring/prefix match can let sibling paths escape the intended root
  • Never infer case-insensitive behavior from process.platform alone: Windows is case-insensitive, but Darwin volumes are not all case-insensitive. APFS and HFS+ can be case-sensitive; a blanket lowercase conversion on macOS can conflate distinct sibling directories.
  • Use filesystem-aware case handling: Only fold case when the relevant volume has been explicitly identified as case-insensitive. Otherwise, compare the resolved path case-sensitively.
  • Current implementation caveat: This is the safe target pattern, not a claim about every existing repository implementation. FSStorageProvider currently folds case for all Darwin paths, so its root confinement is not volume-aware on case-sensitive macOS filesystems.
  • Resolve first, compare second: resolve both paths before comparing; do not compare user input or unresolved relative segments.
  • Root confinement must be exact-match-or-separator: a path is within rootDir only when it equals the normalized root exactly or starts with rootDir + path.sep; a bare substring/prefix match lets /root-escape slip past /root. Filesystem roots are valid roots and must remain exact-match-or-separator checks.
  • Where it matters: security checks such as path-traversal prevention, rootDir confinement, and any validation that a resolved path stays under an allowed directory
  • Pattern:
    import path from 'node:path';
    
    function normalizeForRootComparison(value: string, volumeIsCaseInsensitive = false): string {
      return volumeIsCaseInsensitive ? value.toLowerCase() : value;
    }
    
    function isPathWithin(candidate: string, rootDir: string, volumeIsCaseInsensitive = false): boolean {
      const a = normalizeForRootComparison(path.resolve(candidate), volumeIsCaseInsensitive);
      const b = normalizeForRootComparison(path.resolve(rootDir), volumeIsCaseInsensitive);
      const boundary = b.replace(/[\\/]+$/, '') + path.sep;
      return a === b || a.startsWith(boundary);
    }
    
  • Resolve first, compare second: compare normalized absolute paths; only treat a case mismatch as equivalent when the relevant filesystem volume has already been confirmed to be case-insensitive

Read the full file on GitHub · 124 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. 1mo ago Changed · +38 lines 88bdd5d8d5b9
  2. 1mo ago First seen · 86 lines · 12 tokens per session scan A 56feba86ccb9

Subscribe to this mod's changes

windows-compatibility is a skill published in the GitHub repository bradygaster/squad (3,295 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 1,572 once invoked, about $0.0000 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 2026-08-30.