Autonomous AI agent workflow — file-based UPD/RESULT cycle
Pull GitHub Copilot usage statistics without UI or screenshots. Two Python CLIs: one reads live credit/quota numbers from GitHub's private Copilot API, the other runs fast, context-free queries over the plugin's per-session `main.jsonl` debug log (tokens, requests, tool calls). Use when the user wants to track AI credits, premium-request usage, token counts, or inspect what a chat session actually did.
Export, list, and search GitHub Copilot chat sessions from VS Code (both stable and Insiders) to HTML, JSON, JSONL, or text. Use when the user wants to save, share, back up, summarize, or search past Copilot chat conversations.
Fill a DOCX template interactively — extracts <placeholder> names via CLI, asks the user for each value with vscode_askQuestions, then produces a filled copy. The original template is never modified.
Analyze git commit history to extract SDLC instruction files. Use when: reverse-engineering workflows from commits, extracting coding patterns from diffs, building agent instructions from real code changes, generating automation knowledge base from commit history. Iterates through commits, extracts per-file diffs, invokes Copilot CLI (Claude Opus 4.6) to identify and document reusable SDLC patterns.
Translate any website to any language using Chrome DevTools MCP — the AI model extracts text from the page, translates it, and injects the translation back into the DOM.
Convert a list of markdown files (with images, code blocks, quizzes) into a single landscape DOCX with TOC, page breaks between files, shaded inline-code, and uniform image scaling