VFS — Virtual Function Signatures
> Token-efficient code discovery using AST-extracted function signatures.
Best use case
VFS — Virtual Function Signatures is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
> Token-efficient code discovery using AST-extracted function signatures.
Teams using VFS — Virtual Function Signatures should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/vfs/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How VFS — Virtual Function Signatures Compares
| Feature / Agent | VFS — Virtual Function Signatures | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
> Token-efficient code discovery using AST-extracted function signatures.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# VFS — Virtual Function Signatures > Token-efficient code discovery using AST-extracted function signatures. ## When to Use - Exploring unfamiliar codebases or large files - Understanding module APIs without reading implementation details - Mapping project structure and exports - Pre-reading before targeted file reads (Read tool) - Reducing token usage on code exploration by 60-98% ## Core Concept VFS extracts **exported function, class, and interface signatures** from source files using AST/tree-sitter parsing. Bodies are stripped — you get the shape of code without the implementation. ## Usage ### CLI ```bash # Single file — get all exported signatures vfs src/memory.ts # Directory — recursive scan of all supported files vfs src/ # Specific language filter vfs --lang typescript src/ ``` ### MCP Server Configured in `.mcp.json`. Available as tool calls in Claude Code. ## Supported Languages TypeScript, JavaScript, Python, Go, Rust, Java, C/C++, Ruby, PHP, Swift, Kotlin, Scala, Dart (13 languages). ## Workflow Pattern ### Explore-Then-Read (recommended) 1. `vfs <directory>` — Get structural overview (signatures only) 2. Identify the specific functions/classes you need 3. `Read <file>` with line offsets — Read only the relevant sections ### Compare-APIs 1. `vfs src/old-module.ts` — Get old API surface 2. `vfs src/new-module.ts` — Get new API surface 3. Compare signatures for breaking changes ### Dependency Mapping 1. `vfs src/` — Get all exports across the project 2. Identify which modules export what 3. Trace import chains without reading full files ## Token Savings | File Size | Full Read | VFS | Savings | |-----------|-----------|-----|---------| | 100 lines | ~2K tokens | ~200 tokens | 90% | | 500 lines | ~10K tokens | ~500 tokens | 95% | | 1000+ lines | ~20K tokens | ~800 tokens | 96% | ## Integration Notes - Binary at `~/go/bin/vfs` - MCP config in project `.mcp.json` - Works on any file tree — no project config needed - Output is plain text, one signature per line with file:line prefix
Related Skills
ai-function-calling
AI function calling / tool use patterns — schema definition, tool dispatch, streaming tool calls, and error handling.
ultrathink
UltraThink Workflow OS — 4-layer skill mesh with persistent memory and privacy hooks for complex engineering tasks. Routes prompts through intent detection to activate the right domain skills automatically.
ultrathink_review
Multi-pass code review powered by UltraThink's quality gate — checks correctness, security (OWASP), performance, readability, and project conventions in a single structured pass.
ultrathink_memory
Persistent memory system for UltraThink — search, save, and recall project context, decisions, and patterns across sessions using Postgres-backed fuzzy search with synonym expansion.
ui-design
Comprehensive UI design system: 230+ font pairings, 48 themes, 65 design systems, 23 design languages, 30 UX laws, 14 color systems, Swiss grid, Gestalt principles, Pencil.dev workflow. Inherits ui-ux-pro-max (99 UX rules) + impeccable-frontend-design (anti-AI-slop). Triggers on any design, UI, layout, typography, color, theme, or styling task.
Zod
> TypeScript-first schema validation with static type inference.
webinar-registration-page
Build a webinar or live event registration page as a self-contained HTML file with countdown timer, speaker bio, agenda, and registration form. Triggers on: "build a webinar registration page", "create a webinar sign-up page", "event registration landing page", "live training registration page", "workshop sign-up page", "create a webinar page", "build an event page", "free webinar landing page", "live demo registration page", "online event page", "create a registration page for my webinar", "build a training event page".
webhooks
Webhook design patterns — delivery, retry with exponential backoff, HMAC signature verification, payload validation, idempotency keys
web-workers
Offload heavy computation from the main thread using Web Workers, SharedWorkers, and Comlink — structured messaging, transferable objects, and off-main-thread architecture patterns
web-vitals
Core Web Vitals monitoring (LCP, FID, CLS, INP, TTFB), measurement with web-vitals library, reporting to analytics, and optimization strategies for Next.js
web-components
Native Web Components, custom elements API, Shadow DOM, HTML templates, slots, lifecycle callbacks, and framework-agnostic design patterns
wasm
WebAssembly integration — Rust to WASM with wasm-pack/wasm-bindgen, WASI, browser usage, server-side WASM, and performance considerations