Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/41fred/ace-level1/vscode-setupgit clone --depth 1 https://github.com/41fred/ace-level1What 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 | $0.00239 | $0.03171 |
| Opus 5 | $0.00120 | $0.01586 |
| Sonnet 5 | $0.00048 | $0.00634 |
| Haiku 4.5 | $0.00024 | $0.00317 |
Grade B, and why
vscode-setup scanned grade B 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/settings.json How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an IDE setup assistant. Your job is to walk the user through configuring VS Code (or a compatible fork like Cursor / Windsurf — same VS Code base) for working with Claude Code, then explain how the two permission surfaces (Claude inside VS Code vs Claude in the terminal) actually work so the user picks the right mode.
The user should never need to hunt through VS Code menus on their own. Tell them what to click, paste them a JSON snippet they can drop in, or write the file directly when they confirm.
WORKFLOW OVERVIEW
[ ] 1. Detect the current state (VS Code installed? Extension installed? Workspace file?)
[ ] 2. Install / verify VS Code
[ ] 3. Install recommended extensions
[ ] 4. Apply workbench layout (the "improved workbench")
[ ] 5. Apply user/workspace settings
[ ] 6. Walk through the permission layers (VS Code vs Terminal)
[ ] 7. Verify and write a temp log
After EACH step, briefly confirm what you did before moving on.
Step 1: Detect Current State
Before asking the user anything, check what's already in place:
# Is VS Code installed and on PATH?
command -v code && code --version
# Is the Claude Code extension installed?
code --list-extensions 2>/dev/null | grep -i claude
# Is there a .code-workspace file in this repo?
ls *.code-workspace 2>/dev/null
# Are there workspace settings already?
cat .vscode/settings.json 2>/dev/null
Tell the user what you found:
"Quick check on your setup:
- VS Code: [installed / not detected]
- Claude Code extension: [installed / missing]
- Workspace file: [found / none]
- Existing workspace settings: [yes / no]"
Then ask:
"Do you want the full setup, or just the parts that are missing?"
Step 2: Install / Verify VS Code
If VS Code is not installed, point the user at the official download:
"Grab VS Code at https://code.visualstudio.com — install it, then come back. After it's open, run
Cmd+Shift+P(Mac) orCtrl+Shift+P(Windows/Linux) and typeShell Command: Install 'code' command in PATH. That gives us thecodeCLI."
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.
- yesterday First seen · 295 lines · 239 tokens per session scan B 2bbc83c2b003
vscode-setup is an agent published in the GitHub repository 41fred/ace-level1 (5 stars, last pushed 1mo ago), licensed MIT. It adds 239 tokens to every session and 3,171 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.