Comprehensive analytics dashboard for AI coding agents — Cursor, Windsurf, Claude Code, VS Code Copilot, Zed, Antigravity, OpenCode, Command Code
Coordinated Agent Team is a prompt-driven multi-agent system for autonomous software delivery. It defines clear agent roles, a deterministic workflow, strict I/O contracts, and artifact-based coordination.
A Github Copilot usage analyzer for VS Code.
My GitHub Copilot settings for VS Code
A hyper-optimized MCP server that supercharges AI coding agents. Outperforms built-in IDE tools with AST-based precision editing and native OS control, drastically reducing LLM token consumption.
Multi-transport chat bridge for VS Code Chat. Control your AI coding assistant remotely via Telegram, WhatsApp, Slack, or Discord.
Claude Code plugin that hard-blocks dependency additions, bumps, and downgrades until a fresh, source-cited version check is recorded. Supports npm, pip, Poetry/uv, Cargo, and NuGet.
Full project lifecycle AI workstation — orchestrates Agents, Skills, Hooks & Prompts for end-to-end development workflow, from requirements analysis to delivery. 项目全生命周期 AI 工作站。
AI Agent configuration and policy template for VS Code Copilot and Codex to standardize behavior, enforce safety, and reduce hallucinations.
Research-grade Copilot CLI + VS Code GHCP harness for rigorous multi-LLM collaboration. Enforces multi-turn adversarial debate, transparent assumptions (Decision Cards), and goal-centered research rigor.
Human-in-the-loop feedback for AI coding agents. Pause your agent, give feedback (text + images), get Telegram notifications, reply from your phone. Works with OpenCode (plugin), VS Code Copilot, Claude Desktop (MCP).
Pre-launch Security, UI/UX and shipped-artifact verification for vibe-coded apps: taint analysis, secret + git-history scanning, dependency CVEs, APK/bundle leak detection, SARIF + SBOM, and a 10-stage adversarial audit loop (Claude Code, Copilot, Codex, Cursor, Windsurf, Gemini CLI)
A portable prompt skill to remove yellow/orange/sepia AI color casts from generated images. Works with opencode, Claude Code, Codex, Cursor, Windsurf, VS Code Copilot, and any image generator.
A lightweight black-box agent evaluator using YAML specifications to score task completion.
Unify and analyze AI session data from 16 editors into a single local dashboard showing models, costs, tools, and usage metrics.
To associate your repository with the vscode-copilot topic, visit your repo's landing page and select "manage topics."