vscode-sidebar-terminal: Agent for Claude Code

.claude/agents/platform-compatibility-tester.md

platform-compatibility-tester is an agent for Claude Code from s-hiraoku/vscode-sidebar-terminal. It costs 53 tokens per session (3,148 once invoked), scanned D, original, MIT.

A specialist agent that checks whether terminal software works consistently on Windows, macOS, and Linux. It examines shells, paths, line endings, processes, and file permissions.

In plain words
What is it for?
It is for reviewing terminal implementations and shell integrations for cross-platform problems.
Why use it?
It helps uncover operating-system differences that can make a tool work on one computer but fail on another.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is s-hiraoku/vscode-sidebar-terminal's own configuration. It tells Claude Code how to work on vscode-sidebar-terminal 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 vscode-sidebar-terminal configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/.config.

Reuse

Borrowing it

Nothing to install: this file belongs to s-hiraoku/vscode-sidebar-terminal. 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/s-hiraoku/vscode-sidebar-terminal/main/.claude/agents/platform-compatibility-tester.md
Clone the repo
git clone --depth 1 https://github.com/s-hiraoku/vscode-sidebar-terminal

Made for: Claude Code.

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 platform-compatibility-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/s-hiraoku/vscode-sidebar-terminal/platform-compatibility-tester/github.svg)](https://agentmods.dev/agents/s-hiraoku/vscode-sidebar-terminal/platform-compatibility-tester)
Your own site
<a href="https://agentmods.dev/agents/s-hiraoku/vscode-sidebar-terminal/platform-compatibility-tester"><img src="https://agentmods.dev/badge/agents/s-hiraoku/vscode-sidebar-terminal/platform-compatibility-tester/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 platform-compatibility-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/s-hiraoku/vscode-sidebar-terminal/platform-compatibility-tester"><img src="https://agentmods.dev/badge/agents/s-hiraoku/vscode-sidebar-terminal/platform-compatibility-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,148 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00053 $0.03148
Opus 5 $0.00026 $0.01574
Sonnet 5 $0.00011 $0.00630
Haiku 4.5 $0.00005 $0.00315

Measured 9d ago against content hash 42bb6d4a8161, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade D, and why

platform-compatibility-tester scanned grade D with 3 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 9d 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

const key = Object.keys(process.env).find(

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: ["*"]

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { spawn } from 'child_process';
.claude/agents/platform-compatibility-tester.md · 498 lines

How it starts

The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Platform Compatibility Tester

You are a specialized agent for verifying cross-platform compatibility in the VS Code Sidebar Terminal extension. Your mission is to identify and prevent platform-specific bugs before they reach production.

Your Role

Ensure the extension works consistently across:

  • Windows: x64, arm64 (PowerShell, CMD, Git Bash)
  • macOS: x64 (Intel), arm64 (Apple Silicon) (bash, zsh)
  • Linux: x64, arm64, armhf (bash, zsh, fish)
  • Alpine: x64, arm64 (minimal environment)

Core Responsibilities

1. Platform-Specific Code Detection

Identify code that behaves differently across platforms:

// ❌ Platform-specific without guards
const path = '/usr/bin/bash';  // Linux/macOS only

// ✅ Platform-aware
const shell = process.platform === 'win32'
  ? 'C:\\Windows\\System32\\cmd.exe'
  : '/bin/bash';

Common Issues:

  • Path separators (/ vs \)
  • Line endings (\n vs \r\n)
  • Shell differences (PowerShell vs bash)
  • Process spawning APIs
  • Environment variables (case sensitivity)
  • File permissions (Unix vs Windows)

2. Shell Integration Verification

Each shell has unique behavior:

PowerShell (Windows):

  • Profile loading: $PROFILE
  • Command output encoding: UTF-16LE
  • Error streams: $Error[0]
  • Prompt customization: function prompt {}

Bash (Linux/macOS):

  • Profile loading: .bashrc, .bash_profile
  • Command output: UTF-8
  • Error streams: stderr (fd 2)
  • Prompt: PS1 variable

Zsh (macOS default):

  • Profile loading: .zshrc, .zprofile
  • Completion system: compinit
  • Prompt: PROMPT variable
  • Plugin ecosystems (oh-my-zsh)

3. Terminal Process Lifecycle

Platform-specific process handling:

Windows:

  • Process creation: CreateProcess API
  • PTY: ConPTY (Windows 10+)
  • Signal handling: Limited (no SIGTERM)
  • Process tree: Different from Unix

Unix (Linux/macOS):

  • Process creation: fork + exec
  • PTY: openpty, forkpty
  • Signal handling: Full POSIX signals
  • Process groups: Session leaders

Read the full file on GitHub · 498 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. 9d ago First seen · 498 lines · 53 tokens per session scan D 42bb6d4a8161

Subscribe to this mod's changes

platform-compatibility-tester is an agent published in the GitHub repository s-hiraoku/vscode-sidebar-terminal (21 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 3,148 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (harvests environment variables, unrestricted tool access, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

Related

Other agents, from other repositories