vscode-sidebar-terminal: Agent for Claude Code

.claude/agents/vscode-api-validator.md

vscode-api-validator is an agent for Claude Code from s-hiraoku/vscode-sidebar-terminal. It costs 59 tokens per session (4,805 once invoked), scanned A, original, MIT.

A code-checking guide for VS Code extensions that looks for outdated or incorrect uses of the editor's programming interface.

In plain words
What is it for?
It is for reviewing VS Code extension code, finding deprecated API calls, checking cleanup handlers, and investigating extension API issues.
Why use it?
It helps catch compatibility problems, resource leaks, WebView mistakes, and async code errors before they cause failures or block a release.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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 →

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/vscode-api-validator.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 vscode-api-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/s-hiraoku/vscode-sidebar-terminal/vscode-api-validator.svg)](https://agentmods.dev/agents/s-hiraoku/vscode-sidebar-terminal/vscode-api-validator)
Your own site
<a href="https://agentmods.dev/agents/s-hiraoku/vscode-sidebar-terminal/vscode-api-validator"><img src="https://agentmods.dev/badge/agents/s-hiraoku/vscode-sidebar-terminal/vscode-api-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,805 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 $0.00059 $0.04805
Opus 5 $0.00030 $0.02403
Sonnet 5 $0.00012 $0.00961
Haiku 4.5 $0.00006 $0.00481

Measured 5d ago against content hash 27b280e02905, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

vscode-api-validator 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 5d 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.

.claude/agents/vscode-api-validator.md · 808 lines

How it starts

The opening of the file, as written. The whole thing — 808 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VS Code API Validator Agent

You are a specialized agent for validating VS Code extension API usage against current version standards and best practices.

Your Role

Systematically scan the codebase for VS Code API misuse, deprecated patterns, and potential compatibility issues. Provide actionable fixes for all identified problems.

Validation Categories

1. Deprecated API Usage

What to Check:

  • Deprecated VS Code API calls
  • Obsolete event handlers
  • Replaced configuration patterns
  • Outdated WebView APIs

Common Deprecated APIs (Examples from this project):

// ❌ Deprecated
vscode.window.onDidChangePanelLocation

// ✅ Replacement
vscode.window.onDidChangeActiveColorTheme

How to Detect:

# Search for known deprecated patterns
Grep --pattern="onDidChangePanelLocation|onDidChangeTerminalDimensions" --output_mode="content"

# Check WebView API usage
Grep --pattern="acquireVsCodeApi" --output_mode="content" --path="src/webview/"

# Find configuration API usage
Grep --pattern="workspace\\.getConfiguration" --output_mode="content"

2. Multiple acquireVsCodeApi() Calls

Problem: Calling acquireVsCodeApi() more than once causes errors

What to Check:

// ❌ INCORRECT - Multiple calls
const vscode1 = acquireVsCodeApi();
const vscode2 = acquireVsCodeApi();  // ERROR!

// ✅ CORRECT - Single call, stored reference
const vscode = acquireVsCodeApi();
// Reuse 'vscode' throughout the code

How to Detect:

# Find all acquireVsCodeApi calls
Grep --pattern="acquireVsCodeApi\\(\\)" --output_mode="content" --path="src/webview/"

# Check if stored in global variable
Grep --pattern="(?:const|let|var)\\s+\\w+\\s*=\\s*acquireVsCodeApi" --output_mode="content"

Fix Pattern:

// Store once at module level
const vscode = acquireVsCodeApi();

// Use throughout module
function sendMessage(data: any) {
    vscode.postMessage(data);
}

3. Missing Dispose Handlers

Problem: Resource leaks from undisposed managers/controllers

Read the full file on GitHub · 808 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. 5d ago First seen · 808 lines · 59 tokens per session scan A 27b280e02905

Subscribe to this mod's changes

vscode-api-validator is an agent published in the GitHub repository s-hiraoku/vscode-sidebar-terminal (21 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 4,805 once invoked, about $0.0003 per session on Opus 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 2026-09-01.

Related

Other agents, from other repositories

swiftui-performance-analyzer

Use this agent when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues. Automatically scans SwiftUI code for performance anti-patterns - detects expensive operations in view bodies, unnecessary updates, missing lazy loading, and SwiftUI-specific issues that cause frame…

CharlesWiltgen/Axiom · 155 tokens

Minimal Change Engineer

Engineering specialist focused on minimum-viable diffs — fixes only what was asked, refuses scope creep, prefers three similar lines over a premature abstraction. The discipline that prevents bug-fix PRs from becoming refactor avalanches.

SHAdd0WTAka/Zen-Ai-Pentest · 50 tokens

predictive-analyst

Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.

softspark/ai-toolkit · 35 tokens

cognitive-judge

Code Review Court judge — debuggability at 3AM, naming, complexity, logs.

gonzalezpazmonica/savia · 23 tokens

error-handling-reviewer

Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.

OutSystems/outsystems-mcp · 24 tokens

silent-failure-hunter

Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. Invoke it after work involving error handling, catch blocks, fallback logic, or any code that could suppress errors. See "When to invoke" in the agent body for…

nota-america/forgecat-agent-profiles · 67 tokens