How real projects brief GitHub Copilot, from .github/copilot-instructions.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
SireJeffCopilot instructionsSireJeff/k0ntext/.github/copilot-instructions.md
template-engine/ # Handlebars template system │ ├── template-sync/ # Template synchronization │ ├── utils/ # Utilities (chunking, encoding) │ └── mcp.ts # MCP server ├── bin/ # CLI entry point ├── agents/ # AI agent definitions ├── skills/ # RPI workflow skills ├── templates/ # Context
structured-worldCopilot instructionsstructured-world/gitlab-mcp/.github/copilot-instructions.md
GitHub Copilot Instructions for gitlab-mcp ## Project Overview This is a GitLab MCP (Model Context Protocol) server that provides GitLab API access through standardized MCP tools. The project uses TypeScript
undercoveragentsReads credentialsCopilot instructionsundercoveragents/undercoveragents/.github/copilot-instructions.md
Belongs to `Connector`, schema discovery + visibility, `SchemaIntelligence` + `SqlQueryBroadcasts` concerns, agents, jobs, services, prompts | | `tool_mcp_server` | `mcp_server` | Belongs to `Connector`, discovers MCP tools + manages visibility | | `tool_rag_query
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
AWSCopilot instructionsawslabs/service-onboarding-accelerator-on-aws/.github/copilot-instructions.md
state is written to `.service-approval/ /` (per-service layout) in the current working directory. ## MCP servers Registered via `.vscode/mcp.json`. Confirm these are reachable before starting the skill: - `aws-documentation` (stdio
bvenkataCopilot instructionsbvenkata/legacy2mcp/.github/copilot-instructions.md
plain website with no API docs into a safe, typed, audit-logged MCP server -- read-only by default, every call audit-logged, no hand-written adapter code or hand-maintained
drknowhowReads credentialsCopilot 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
sumithrCopilot instructionssumithr/sumo-qa/.github/copilot-instructions.md
test data, deciding QA approach), call the relevant skill tool on the `sumo-qa` MCP server and follow the checklist it returns. Available skills (each registered as an MCP tool
u9401066Copilot instructionsu9401066/zotero-keeper/.github/copilot-instructions.md
exact read or authorization; every mutation preview and confirmed execution carries it as `expected_server_id` - Every mutation first returns a complete proposal with `confirmation_required=true`; obtain user approval before
AraszCopilot instructionsArasz/ai-raccoon/.ai-badger/copilot-instructions.md
AiRaccoon C# .NET 10 MCP server exposing agent memory management over sqlite-memory: project-scoped memory bank, workspace sandboxes, shared promotion tier, hybrid search, degradation, and optional cloud sync. > Domain
AraszCopilot instructionsArasz/ai-raccoon/.github/copilot-instructions.md
AiRaccoon C# .NET 10 MCP server exposing agent memory management over sqlite-memory: project-scoped memory bank, workspace sandboxes, shared promotion tier, hybrid search, degradation, and optional cloud sync. > Domain
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/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
mrcbrbn5361Reads credentialsCopilot 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
Chiru144Copilot instructionsChiru144/Spotify-MCP-Web-And-MCP-Server/.github/copilot-instructions.md
reorder, shuffle, search, discover music, or do any other Spotify action, check the available MCP tools (including the standard `spotify_*` tools like `spotify_get_my_playlists`, `spotify_get_playlist`, `spotify
danchevCopilot instructionsdanchev/openmarkets/.github/copilot-instructions.md
Copilot Instructions for OpenMarkets ## Project Overview - **OpenMarkets** is a Model Context Protocol (MCP) server for agentic retrieval of financial data from Yahoo Finance, designed for LLM and agentic workflows (Claude
filt3rrReads credentialsCopilot instructionsfilt3rr/vael/.github/copilot-instructions.md
overlay (`overlay.py`) and a background notifier (`notifier.py`) that pushes Discord/overlay alerts. ## Project layout - `src/eve_agent/server.py` — MCP server entrypoint registering all tools via `@mcp.tool()` - `src/eve_agent/tools/` — domain modules: `character.py`, `market.py`, `industry.py`, `skills.py`, `intel.py
humanity4aiReads credentialsCopilot instructionshumanity4ai/project_human/.github/copilot-instructions.md
research-driven implementation. ## Repo specifics - pnpm monorepo: `@humanity4ai/mcp-servers` (publishable, `dist/` committed) + `@humanity4ai/evals` - Rule-based MCP server — NO LLM calls in handlers; patterns live in `src/patterns.ts` - Crisis resources only in `src/crisis-resources.ts
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.
