How real projects brief GitHub Copilot, from .github/copilot-instructions.md.
shigechikaCopilot instructionsshigechika/mcp-stdio/.github/copilot-instructions.md
serve`) — the mirror image (server side: HTTP in, stdio out): spawns a local stdio MCP server as a child process and publishes it as a Streamable HTTP endpoint so clients
suryastCopilot instructionssuryast/indonesia-civic-stack/.github/copilot-instructions.md
scraper.py` — fetch() and search() functions - `normalizer.py` — raw HTML/JSON → dict transformations - `router.py` — FastAPI routes - `server.py` — MCP server using CivicStackMCPBase - `app.py` — FastAPI app - `README.md` — module docs See `AGENTS.md` for full architecture guide
ajbmachonCopilot instructionsajbmachon/ajbm-skills/.github/copilot-instructions.md
JSONL - AI-optimized CLI with JSON output - Built-in daemon for background operations - MCP server integration for Claude and other AI assistants ## Issue Tracking with bd **CRITICAL**: This project uses
drknowhowCopilot instructionsdrknowhow/code-context-control/.github/copilot-instructions.md
every session. 2. **VERIFY**: confirm tools such as `mcp_c3_c3_search` and `mcp_c3_c3_read` are available before proceeding. ## C3 Tools — MANDATORY (workflow rule — no hooks in this
MicrosoftCopilot instructionsmicrosoft/ContextShare/.github/copilot-instructions.md
This VS Code extension manages AI assistant catalog resources (chat modes, instructions, prompts, tasks, MCP servers) across multiple repositories. It provides centralized discovery, activation, and "Hats" (preset) functionality
Poorgramer-ZackCopilot instructionsPoorgramer-Zack/dart-expert-skills/.github/copilot-instructions.md
kebab-case for file and directory names - Keep skills atomic - one skill per technology/framework ## MCP Servers This repository uses two MCP servers (configured in `.mcp.json`): - **exa**: Web search and content
sbroenneCopilot instructionssbroenne/pytest-skill-engineering/.github/copilot-instructions.md
CRITICAL: What We Test **We do NOT test agents. We USE agents to test:** - **MCP Servers** — Can an LLM understand and use these tools? - **CLI Tools** — Can an LLM operate
MicrosoftCopilot instructionsmicrosoft/PHIDeIDPortal/.github/copilot-instructions.md
Whenever making any Azure MCP server calls, you should always use the subscription ID of 5669097f-9a99-4354-b528-addefc61d776 and tenant ID of 16b3c013-d300-468d-ac64-7eda0820b6d3. Always
mrcbrbn5361Copilot instructionsmrcbrbn5361/SyncytiumMD/.github/copilot-instructions.md
syncytium sync` — never edit those by hand. ## Overview SyncytiumMD is a CLI + library + MCP server that maintains one canonical context (`.syncytium/`) and transpiles it into the native instruction format
jyunmingCopilot instructionsjyunming/Axon/.github/copilot-instructions.md
Names (30 total — agent mode) When using Copilot in **agent mode** with the Axon MCP server, use these tool names (they differ deliberately from the OpenAI-format `tools.py` names): ### Ingestion
MicrosoftCopilot instructionsmicrosoft/ACES/.github/copilot-instructions.md
tests/` | Test suite organized by component | ## Architecture Overview ``` Inspect AI → SABERSandboxEnvironment → ClientSessionManager → REST/MCP Server ↓ ↓ ↓ Agent Solver MCP Client SessionManager ↓ ↓ ↓ Tool Execution Tool Discovery Docker Sandbox Execution ``` **Key Components**: - `SABERSandboxEnvironment`: Inspect
MicrosoftCopilot instructionsmicrosoft/frontier-agentic-cobuild-rvas/.github/copilot-instructions.md
fast-moving Azure / Foundry capability: 1. **Search Microsoft Learn through the `microsoft-docs` MCP server** (the MS Learn MCP server) for the **current** API surface, SDK syntax, and product guidance
RevealUIStudioCopilot instructionsRevealUIStudio/revealui/.github/copilot-instructions.md
Purpose: give an AI coding agent concise, actionable context to be productive in this monorepo.
2aronSCopilot instructions2aronS/org-mcp/.github/copilot-instructions.md
mcp org-mcp is a Rust Model Context Protocol (MCP) server for org-mode knowledge management. It provides search, content access, and note linking capabilities for org-mode files through
agentic-dev-ioCopilot instructionsagentic-dev-io/agent-farm/.github/copilot-instructions.md
this repository. Follow these instructions exactly to handle onboarding, Context7 MCP, and the Serena MCP server so that Copilot can use them reliably. ## Quick Reference: Agent-Farm Technical Overview **agent
AppsYogi-comCopilot instructionsAppsYogi-com/gsc-mcp-server/.github/copilot-instructions.md
MCP Copilot Instructions ## Project Overview This is a **Model Context Protocol (MCP) server** that provides Google Search Console (GSC) API access to AI clients (Claude, Cursor, VS Code Copilot
azank1Copilot instructionsazank1/cdv/.github/copilot-instructions.md
Agent Instructions CDV is an MCP server for prompt quality, refinement loops, and Conservative Dual-Verify agent-loop control. See [README.md](../README.md) for architecture, tools, and examples. --- ## Required on every
BogzxCopilot instructionsBogzx/LearnLoop/.github/copilot-instructions.md
Trailhead coaching — always on, never block Five MCP tools: `coach`, `wiki_lookup`, `wiki_save`, `wiki_bootstrap`, `wiki_proven_prompts`. These tools are NOT optional. They REPLACE native Read/Grep/Glob/file-search
djerokCopilot instructionsdjerok/glm-mcp/copilot/copilot-instructions.md
delegation You have the **glm** MCP server available in agent mode, with these tools: `glm_agent`, `glm_delegate`, `glm_recommend`, `glm_status`. GLM (Zhipu/Z.ai) is **~10× cheaper** than the default
dmgrokCopilot instructionsdmgrok/mcp_mother_skills/.github/copilot-instructions.md
tech stack detection. It supports both Claude and GitHub Copilot agents. ### Core Architecture ``` index.ts → MCP server entry, tool definitions, request routing ├── agent-detector.ts → Detects Claude vs Copilot (env vars, client info
Repository-wide instructions for GitHub Copilot, kept in .github/copilot-instructions.md.
How to build and test, the project's structure, and the conventions Copilot should follow in suggestions and reviews.
No. Copilot's coding agent also reads AGENTS.md, so many projects keep the shared rules there.
Open a file to see its discussion. Reports from people and their agents are coming.
