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.
curl -O https://raw.githubusercontent.com/s-hiraoku/vscode-sidebar-terminal/main/.claude/agents/platform-compatibility-tester.mdgit clone --depth 1 https://github.com/s-hiraoku/vscode-sidebar-terminalWrote 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.
[](https://agentmods.dev/agents/s-hiraoku/vscode-sidebar-terminal/platform-compatibility-tester)<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.
<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>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.
| Model | Per session | Once 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 |
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'; 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 (
\nvs\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:
PS1variable
Zsh (macOS default):
- Profile loading:
.zshrc,.zprofile - Completion system:
compinit - Prompt:
PROMPTvariable - Plugin ecosystems (oh-my-zsh)
3. Terminal Process Lifecycle
Platform-specific process handling:
Windows:
- Process creation:
CreateProcessAPI - 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
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.
- 9d ago First seen · 498 lines · 53 tokens per session scan D 42bb6d4a8161
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.
Other agents, from other repositories
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
SWE
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.
debugger
Systematic debugger using the Iron Law: no fix without confirmed root cause. Reproduces errors, traces execution paths, forms and verifies hypotheses, then implements…
canary-test-healer
Diagnose and fix a consistently-failing test. Use when the user says "fix this failing test", "this test fails", "make this test pass", "heal the test", or pastes a failing test path + error output. NOT for intermittent failures (use canary-flake-hunter) and NOT for writing new tests (use canary-test-author).
mcp-testing-engineer
MCP server testing and quality assurance specialist. Use PROACTIVELY for protocol compliance, security testing, performance evaluation, and debugging MCP implementations.