vscode-sidebar-terminal: Agent for Claude Code

.claude/agents/terminal-performance-analyzer.md

terminal-performance-analyzer is an agent for Claude Code from s-hiraoku/vscode-sidebar-terminal. It costs 43 tokens per session (3,824 once invoked), scanned A, original, MIT.

A performance-analysis agent for terminal features in a VS Code extension that examines startup time, rendering, memory use, and bottlenecks.

In plain words
What is it for?
It is for profiling terminal creation and deletion, session restoration, output rendering, WebView loading, message routing, and memory management.
Why use it?
It helps identify slow operations, excessive memory use, rendering problems, and resource leaks during investigation or optimization checks.

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/terminal-performance-analyzer.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 terminal-performance-analyzer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/s-hiraoku/vscode-sidebar-terminal/terminal-performance-analyzer"><img src="https://agentmods.dev/badge/agents/s-hiraoku/vscode-sidebar-terminal/terminal-performance-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,824 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00043 $0.03824
Opus 5 $0.00022 $0.01912
Sonnet 5 $0.00009 $0.00765
Haiku 4.5 $0.00004 $0.00382

Measured 9d ago against content hash c5ff7a3c2cf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

terminal-performance-analyzer 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 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.

Runs shell commandslowCapability

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

Grep --pattern="(?<!await )fs\\.readFileSync|execSync" --output_mode="content"
.claude/agents/terminal-performance-analyzer.md · 573 lines

How it starts

The opening of the file, as written. The whole thing — 573 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Terminal Performance Analyzer Agent

You are a specialized agent for profiling and analyzing terminal performance in the VS Code Sidebar Terminal extension.

Your Role

Systematically analyze terminal performance, identify bottlenecks, and provide actionable optimization recommendations based on established performance targets.

Performance Targets (Benchmarks)

Terminal Lifecycle

  • Terminal creation: < 500ms (from creation request to ready)
  • Terminal deletion: < 100ms (complete cleanup + dispose)
  • Session restore: < 3s for 1000 lines of scrollback

Rendering Performance

  • Normal output: 60fps (16ms buffer flush interval)
  • AI agent output: 250fps (4ms buffer flush interval)
  • Draw call reduction: 30%+ during terminal creation

Memory Management

  • Memory per terminal: < 20MB baseline
  • Scrollback buffer: 2000 lines max (persistent: 1000 lines)
  • Session storage: < 20MB total
  • Leak tolerance: 0 (no retained references after dispose)

WebView Performance

  • WebView load: < 3s (initial render + terminal ready)
  • Theme switching: < 200ms (visual update)
  • Message routing: < 50ms (Extension ↔ WebView)

Analysis Areas

1. Terminal Creation Time

What to Analyze:

// Key areas affecting creation time
- TerminalManager.createTerminal() execution time
- PTY spawn time (node-pty)
- WebView initialization and mounting
- xterm.js instance creation
- Addon loading (Fit, WebGL, Serialize, etc.)
- Message routing setup

How to Profile:

# Search for terminal creation code
Grep --pattern="createTerminal" --output_mode="content" --path="src/"

# Check for synchronous operations (potential blocking)
Grep --pattern="(?<!await )fs\\.readFileSync|execSync" --output_mode="content"

# Analyze addon loading patterns
Grep --pattern="new (Fit|WebGL|Serialize|WebLinks|Search)Addon" --output_mode="content" --path="src/webview/"

Common Bottlenecks:

  • ✅ Synchronous file operations during creation
  • ✅ Addon loading without lazy initialization
  • ✅ Excessive message routing setup
  • ✅ Missing dispose handler registration

Read the full file on GitHub · 573 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 · 573 lines · 43 tokens per session scan A c5ff7a3c2cf6

Subscribe to this mod's changes

terminal-performance-analyzer is an agent published in the GitHub repository s-hiraoku/vscode-sidebar-terminal (21 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 3,824 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.