Reference
VS Code extension
Version 2.0.0. The extension runs the PromptFlow Engine in-process: no server, no Python, no model calls. It is distributed as a .vsix package; it is not on the Visual Studio Marketplace yet.
Install
shell
git clone https://github.com/vijayrajpalanisamy88/Prompt.git && cd Prompt
corepack enable && pnpm install
pnpm --filter ide-extension build
cd apps/vscode-extension && pnpm exec vsce package --no-dependencies
code --install-extension ide-extension-2.0.0.vsixWhat it does
- Optimize sidebar: paste a prompt and run the staged pipeline with token and estimated cost savings.
- Codebase → Prompt: describe a task and generate a prompt with the relevant files from your workspace as context.
- Privacy guard: before sending to AI Chat, scans for credentials and personal data. Modes:
strict(block),redact(default, replace with placeholders),warn(ask). - Status bar: the last optimization result; click to re-run.
- Copilot agent mode: on activation it registers the bundled MCP server in
.vscode/mcp.json(requiresnodeon PATH). See MCP server.
Commands
PromptFlow: Optimize PromptPromptFlow: Validate PromptPromptFlow: Compare Original vs OptimizedPromptFlow: Copy Optimized PromptPromptFlow: Generate Prompt from CodebasePromptFlow: Generate Prompt from Selection
Settings
| Setting | Default | Purpose |
|---|---|---|
promptflow.mcpServerCommand | "node" | Advanced: overrides the command used to launch the external MCP server registered for GitHub Copilot Agent mode (.vscode/mcp.json). The sidebar and PromptFlow: commands don't use this — they run in-process. Leave unset to use the bundled server. |
promptflow.mcpServerArgs | [] | Advanced: arguments for promptflow.mcpServerCommand. Leave unset to use the bundled server. |
promptflow.defaultProvider | "gpt" | Provider used for token estimation when none is specified. |
promptflow.codebaseMaxFiles | 2000 | Maximum number of files scanned per Codebase → Prompt run, before relevance filtering. |
promptflow.codebaseMaxRelevantFiles | 12 | Maximum number of files included as relevant context in a generated prompt. |
promptflow.privacy.enabled | true | Scan prompts for sensitive data (credentials, PII, cloud secrets) before they're sent to AI Chat or copied for that purpose. |
promptflow.privacy.mode | "redact" | How PromptFlow reacts when sensitive data is detected in an outbound prompt. |
promptflow.privacy.exclusions | [] | Exact substrings that should never be treated as sensitive (e.g. a shared team email alias). |
promptflow.privacy.customPatterns | [] | Additional organization-specific sensitive-data patterns, detected alongside the built-in ones. |
Changes in 2.0
- The analysis, optimization, and privacy detectors now come from the shared engine, the same code as the website, CLI, and MCP server.
- Code blocks, inline code, and quoted text inside prompts are never modified by optimization.
- Prompt-injection matches are reported as critical issues but no longer block optimization.
- GPT token counts use
o200k_base(GPT-4o family). Claude, Gemini, and Bedrock counts are labeled approximate. - New MCP tools:
evaluate_prompt,compare_prompts,scan_prompt_security.