agentmods.dev

rag-code-mcp copilot-instructions.md

Rules for GitHub Copilot when working on RagCode MCP, a server that searches local source code by meaning. They require using its code-search tools instead of guessing how the code works.

In plain words
What is it for?
Use them when locating code, understanding functions, choosing the current CodeChunk data structure, or working with Go, PHP, Python, and HTML analysis.
Why use it?
They help the assistant base answers and edits on the actual indexed code, including the correct workspace and implementation details.

Instructions file for GitHub Copilot

53 +1 15d ago A scan 568 tokens original MIT
View the source file doITmagic/rag-code-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/doitmagic/rag-code-mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/doITmagic/rag-code-mcp

Made for: GitHub Copilot.

Per session 568 This file is loaded in full into every session.
When invoked 568 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00568 $0.00568
Opus 5 $0.00284 $0.00284
Sonnet 5 $0.00114 $0.00114
Haiku 4.5 $0.00057 $0.00057

Measured 2d ago against content hash 7b4803c02b08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rag-code-mcp copilot-instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/copilot-instructions.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions - RagCode MCP

⚖️ The Golden Rule

For any information about the code (location, structure, logic, or usage), you MUST use RagCode MCP tools. Never guess code details from memory; always search the local index first.

Project Overview

RagCode is a Model Context Protocol (MCP) server that provides semantic code search (RAG) for local codebases using Ollama (embeddings) and Qdrant (vector storage). It supports multiple languages through a pluggable analyzer architecture.

Architecture & Patterns

  • Core Components:
    • Indexer: Orchestrates analysis, embedding, and storage.
    • PathAnalyzer: Interface for language-specific AST analysis (Go, PHP/Laravel, Python, HTML).
    • CodeChunk: The canonical v2 data structure for all indexed code symbols (functions, types, files).
    • Workspace.Manager: Handles multi-workspace multi-language isolation via language-specific Qdrant collections.
  • Data Flow: Tools -> Workspace.Manager.DetectWorkspace -> Language Detection -> Qdrant Collection (ragcode-{id}-{lang}) -> Search Results.
  • Convention: The project is migrating from APIChunk to CodeChunk. Always use CodeChunk for new features.

Developer Workflows

  • Build/Install: Use go run ./cmd/install/main.go to build binaries and configure local IDEs.
  • Runtime Binaries: Installed to ~/.local/share/ragcode/bin/ by default.
  • Testing: Use standard go test ./.... Use t.TempDir() for workspace/filesystem isolation.
  • Logging: MCP server logs to mcp.log next to the executable. Check MCP_LOG_LEVEL=debug for issues.

MCP Tools Usage

  • search_code: Use as the primary entry point for exploration. Crucial: Always provide the file_path parameter as it's used for workspace and language detection.
  • index_workspace: Triggered automatically on first query per workspace, but can be manually invoked for major changes.

Integration Points

  • Ollama: Requires phi3:medium (reasoning) and mxbai-embed-large (embeddings) by default.
  • Qdrant: Runs in Docker as ragcode-qdrant on port 6333.

Read the full file on GitHub · 34 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 34 lines · 568 tokens per session scan A 7b4803c02b08

Subscribe to this mod's changes

rag-code-mcp copilot-instructions.md is an instructions file published in the GitHub repository doITmagic/rag-code-mcp (53 stars, last pushed 15d ago), licensed MIT. It adds 568 tokens to every session, about $0.0028 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agentsData and AIRAG and vectorsclaude-desktopcode-navigationcursor-idegohtml
Related

Other instructions, from other repositories

hyperframes CLAUDE.md

Claude Code instructions for heygen-com/hyperframes, covering hyperframes, skills, creation workflows, domain skills (loaded on demand) and skill catalog maintenance.

heygen-com/hyperframes · 2,667 tokens

warden AGENTS.md

Instructions for stephnangue/warden, covering warden — agent guide, where to start, the agent loop, provider skills and adding a skill for a new provider.

stephnangue/warden · 1,063 tokens

agent-lsp CLAUDE.md

Instructions for blackwell-systems/agent-lsp, a project described as: MCP server that orchestrates language servers into agent-native workflows. 65 tools, 30 CI-verified languages.

blackwell-systems/agent-lsp · 1,077 tokens

uzomuzo-oss agent-orchestration.instructions.md

Instructions for future-architect/uzomuzo-oss, covering agent orchestration, agent invocation, available subagent types, available skills and immediate agent usage.

future-architect/uzomuzo-oss · 2,187 tokens

uzomuzo-oss AGENTS.md

AGENTS.md instructions for future-architect/uzomuzo-oss, covering agents.md, build & test, architecture (ddd), language policy and rules — read before you write code.

future-architect/uzomuzo-oss · 1,190 tokens

gitlab-mcp-server mcp-best-practices.instructions.md

MCP protocol-level best practices for tool design, annotations, response formats, pagination, and security. Applies to all Go MCP server code.

jmrplens/gitlab-mcp-server · 1,183 tokens