teamfuse
agentdmai/teamfuse/.github/copilot-instructions.md
auto-loaded natively; `--resume= ` for cross-tick context continuity; `--additional-mcp-config @.mcp.json` for MCP servers; `clear-session` drops the session ID (fresh context next tick
How real projects brief GitHub Copilot, from .github/copilot-instructions.md.
agentdmai/teamfuse/.github/copilot-instructions.md
auto-loaded natively; `--resume= ` for cross-tick context continuity; `--additional-mcp-config @.mcp.json` for MCP servers; `clear-session` drops the session ID (fresh context next tick
Hack23/euparliamentmonitor/.github/copilot-instructions.md
start of every session:** 1. **`.github/workflows/copilot-setup-steps.yml`** - Workflow configuration and permissions 2. **`.github/copilot-mcp.json`** - MCP server configuration and available tools 3. **`README.md`** - Project overview, features, and documentation links 4. **`.github/skills/`** - Skills library
putervision/agent-reasoning-mcp/.github/copilot-instructions.md
purge sensitive or secret states from storage. ### 2. Tool Reference Summary (15 Core MCP Tools) * `analyze_screenshot`: Ingest screenshot(s) (single or batch via `items`), lookup cache, return layout description
hby7921/BannerlordSage/.github/copilot-instructions.md
BannerlordSage Copilot Instructions This repository is a Windows-first MCP server for **Mount & Blade II: Bannerlord**. Before suggesting install or usage steps: 1. Read `AGENTS.md` 2. Read `README.md` 3. Read
louagej/al-go-mcp-server/.github/copilot-instructions.md
MCP Server — Copilot Instructions This workspace is the **AL-Go MCP Server** project. It provides MCP tools for AL-Go documentation, domain specialists, and knowledge sources. ## Always use `alg-*` tools
mick-gsk/drift/.github/copilot-instructions.md
Version aus Workspace installieren / auffrischen drift --version # Muss mit pyproject.toml uebereinstimmen ``` Der MCP-Server in `.vscode/mcp.json` zeigt auf das Workspace-venv und ist immer automatisch aktuell, wenn `pip install
putervision/behavior-mcp/.github/copilot-instructions.md
purge sensitive or secret states from storage. ### 2. Tool Reference Summary (15 Core MCP Tools) * `analyze_screenshot`: Ingest screenshot(s) (single or batch via `items`), lookup cache, return layout description
sailro/HttpProxyMcp/.github/copilot-instructions.md
Copilot Instructions — HttpProxyMcp An HTTP/HTTPS MITM proxy with full traffic capture, exposed as an MCP server so LLMs can inspect, filter, and analyze network traffic. Built with
utk09-NCL/mini-memory-mcp/.github/copilot-instructions.md
Mini Memory MCP This project uses a local persistent memory server. Follow these rules in every session. ## Startup - always do this first Call `memory_list` at the start of every
alexey-pelykh/lhremote/.github/copilot-instructions.md
Purpose | |---------|---------| | `packages/core` | CDP client, account/campaign services, feed parsing | | `packages/mcp` | Model Context Protocol server exposing core as MCP tools | | `packages/cli` | CLI entry point (`lhremote` command) | | `packages/lhremote` | Umbrella package re-exporting core
CrestApps/CrestApps.AgentSkills/.github/copilot-instructions.md
first build - No runtime code — purely for local AI authoring 4. **`CrestApps.AgentSkills.Mcp.OrchardCore`** - Runtime MCP server for Orchard Core - Extends `CrestApps.AgentSkills.Mcp` with Orchard Core–specific convenience wrappers - Bundles both `orchardcore
omgwtfwow/mcp-crawl4ai-ts/.github/copilot-instructions.md
BASE_URL` unset; fails fast if missing. Passes env + version into `Crawl4AIServer`. - `src/server.ts`: registers MCP tools, keeps a `Map<string, SessionInfo>` for persistent browser sessions, and uses `validateAndExecute` (Zod parse
zpratt/lousy-agents/.github/copilot-instructions.md
cases, gateways, and formatters cli/ Published CLI package and reference scaffold templates mcp/ Published MCP server package action/ Private GitHub Action package agent-shell/ Published npm script-shell telemetry package
alxpark/propresenter-mcp/.github/copilot-instructions.md
ProPresenter MCP Server Project ## Checklist - [x] Create copilot-instructions.md file in the .github directory - [ ] Get project setup information for MCP server - [ ] Create package.json with dependencies - [ ] Create TypeScript configuration - [ ] Create MCP server
Azure/multi-agent-doc-research/.github/copilot-instructions.md
Multi-Agent Collaboration → Response ├─ Web Search (Bing) ├─ AI Search (Azure AI Search) └─ YouTube Search (MCP Server) ``` ## Dual Orchestration Architectures ### 1. Agent Framework (`services_afw/`) - Production Pattern - **Pattern**: Executor-based workflow
tygryso/hypotree/.github/copilot-instructions.md
data-quality warnings) and the gate decision reference (criteria 1a/1b/2/3/4 with thresholds). ### hypotree@dev — MCP Server Agent Instructions **hypotree** is a persistent hypothesis-DAG orchestrator. It remembers what
aixolotl/microsoft-planner-mcp/.github/copilot-instructions.md
Microsoft Planner MCP — Copilot Instructions ## Project Overview MCP server for Microsoft Planner built with FastMCP and Microsoft Graph SDK. Authenticates via Azure Entra ID On-Behalf-Of flow. ## Stack - **Python
caiowilson/MCP-memento/.github/copilot-instructions.md
search`). ## Project architecture (big picture) - Entrypoint is [cmd/server/server.go](cmd/server/server.go#L1): `app.Run()` wires up the MCP server. - The MCP server lives in [internal/mcp/server.go](internal/mcp/server.go#L1): JSON-RPC over stdio, tool registry
dryvist/nix-ai/.github/copilot-instructions.md
Repository Purpose nix-ai is an AI CLI ecosystem (Claude Code, Antigravity, Codex, Copilot, MCP servers, MLX inference) delivered as Nix home-manager modules. It exports modules consumed
microsoft/ACESEvals/.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
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.