vscode ai-customization.instructions.md

Architecture documentation for VS Code’s AI Customization view, which lets users find and manage files that change AI prompts or behavior, such as agents, skills, instructions, and prompts.

In plain words
What is it for?
Use it when changing the AI Customization view, its category and storage hierarchy, file opening, or handling of customization files.
Why use it?
It explains where these customization files come from and how they are organized, so changes fit the view’s tree and refresh behavior.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/microsoft/vscode/ai-customization
Clone the repo
git clone --depth 1 https://github.com/microsoft/vscode

Made for: GitHub Copilot.

Per session 1,779 This file is loaded in full into every session.
When invoked 1,779 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01779 $0.01779
Opus 5 $0.00890 $0.00890
Sonnet 5 $0.00356 $0.00356
Haiku 4.5 $0.00178 $0.00178

Measured yesterday against content hash 8f953b736981, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vscode ai-customization.instructions.md 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 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.github/instructions/ai-customization.instructions.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Customization View

The AI Customization view provides a unified view for discovering and managing AI customization 'artifacts' (customizations that augment LLM prompts or behavior).

Examples of these include: Custom Agents, Skills, Instructions, and Prompts. It surfaces prompt files that are typically hidden in .github/ folders, user data directories, workspace settings, or exposed via extensions.

Overview

The view displays a hierarchical tree structure:

AI Customization (View Container)
└── AI Customization (Tree View)
    ├── Custom Agents (.agent.md files)
    │   ├── Workspace
    │   │   └── agent files...
    │   ├── User
    │   │   └── agent files...
    │   └── Extensions
    │       └── agent files...
    ├── Skills (SKILL.md files)
    │   └── (same storage structure)
    ├── Instructions (.instructions.md files)
    │   └── (same storage structure)
    └── Prompts (.prompt.md files)
        └── (same storage structure)

Key Features:

  • 3-level tree hierarchy: Category → Storage Group → Files
  • Auto-expands category nodes on initial load and refresh to show storage groups
  • Symbol-based root element for type safety
  • Double-click to open files in editor
  • Context menu support with Open and Run Prompt actions
  • Toolbar actions: New dropdown, Refresh, Collapse All
  • Skill names parsed from frontmatter with fallback to folder name
  • Responsive to IPromptsService change events

File Structure

All files are located in src/vs/workbench/contrib/chat/browser/aiCustomization/:

aiCustomization/
├── aiCustomization.ts              # Constants, IDs, and MenuIds
├── aiCustomization.contribution.ts # View registration and actions
├── aiCustomizationViews.ts         # Tree view pane implementation
├── aiCustomizationIcons.ts         # Icon registrations
└── media/
    └── aiCustomization.css         # Styling

Key Constants (aiCustomization.ts)

  • AI_CUSTOMIZATION_VIEWLET_ID: View container ID for sidebar
  • AI_CUSTOMIZATION_VIEW_ID: Unified tree view ID
  • AI_CUSTOMIZATION_STORAGE_ID: State persistence key
  • AICustomizationItemMenuId: Context menu ID
  • AICustomizationNewMenuId: New item submenu ID

Read the full file on GitHub · 225 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. yesterday First seen · 225 lines · 1,779 tokens per session scan A 8f953b736981

Subscribe to this mod's changes

vscode ai-customization.instructions.md is an instructions file published in the GitHub repository microsoft/vscode (190,061 stars, last pushed yesterday), licensed MIT. It adds 1,779 tokens to every session, about $0.0089 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 2026-08-30.