agentmods.dev

ragdocs-mcp copilot-instructions.md

Project instructions for Ragdocs MCP, a local document-search server that lets AI assistants search Markdown files through the Model Context Protocol. They explain its hybrid search, indexing, graph, memory, web, and Python architecture.

In plain words
What is it for?
Use them when developing Ragdocs MCP to locate interface, core, indexing, parsing, search, and web components and understand its tests, tools, and data flow.
Why use it?
They give an AI coding agent the project overview, technology choices, source layout, and expected conventions before making changes. This makes it easier to work on the correct layer without misunderstanding how search and indexing fit together.

Instructions file for GitHub Copilot

2 6d ago A scan 1,800 tokens original MIT
View the source file andnp/ragdocs-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/andnp/ragdocs-mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/andnp/ragdocs-mcp

Made for: GitHub Copilot.

Per session 1,800 This file is loaded in full into every session.
When invoked 1,800 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 $0.01800 $0.01800
Opus 5 $0.00900 $0.00900
Sonnet 5 $0.00360 $0.00360
Haiku 4.5 $0.00180 $0.00180

Measured 2d ago against content hash 6e8ef6cf83f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ragdocs-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 · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions for mcp-markdown-ragdocs

Project Overview

mcp-markdown-ragdocs is a local-first RAG server providing semantic search over Markdown documentation via the Model Context Protocol (MCP). It combines vector search (FAISS), keyword search (Whoosh BM25), and graph traversal (NetworkX) using Reciprocal Rank Fusion.

Core Features: Hybrid search, git history search, AI memory bank with time range filtering, zero-config auto-indexing, multi-project support

Technology Stack

Language: Python 3.13+ (modern typing with list[T], dict[K,V], T | None) Search: FAISS (vectors), Whoosh (BM25), NetworkX (graph) Parsing: tree-sitter (Markdown AST) MCP: stdio protocol via mcp SDK Web: FastAPI (optional HTTP interface) Tools: uv (package manager), pytest (testing), ruff (linting), Pyrefly (type checking)

Architecture

Four Layers:

  1. Interface: src/mcp_server.py (MCP tools), src/server.py (FastAPI)
  2. Core: src/context.py (singleton state), src/config.py (TOML config), src/models.py (dataclasses)
  3. Indexing: src/indexing/manager.py (coordinator), src/parsers/ (pluggable), src/chunking/ (hierarchy-aware)
  4. Search: src/search/orchestrator.py (parallel + RRF fusion), src/search/pipeline.py (dedup, MMR)

Multiprocess Mode (default): Main process handles MCP protocol with read-only indices; worker process handles indexing. See src/ipc/, src/worker/, src/reader/. Disable with worker.enabled = false.

Key Patterns: Protocol-based abstractions, async-first with asyncio.gather(), dataclass configs, singleton coordination, lazy initialization

Project Layout

src/
├── cli.py                    # Click commands (run, mcp, query, rebuild-index)
├── mcp_server.py            # MCP tool registration and handlers
├── server.py                # FastAPI HTTP server
├── context.py               # ApplicationContext singleton
├── config.py                # TOML config loading, project detection
├── models.py                # Document, Chunk, ChunkResult dataclasses
├── lifecycle.py             # LifecycleCoordinator (shutdown, worker management)
├── chunking/                # HeaderChunker (preserves hierarchy)
├── git/                     # Commit indexing, search, watching
├── indexing/                # IndexManager, FileWatcher, reconciliation
├── indices/                 # VectorIndex (FAISS), KeywordIndex (Whoosh), GraphStore (NetworkX)
├── ipc/                     # Inter-process communication (commands, queues, sync)
├── memory/                  # AI memory bank (CRUD, search, graph linking)
├── parsers/                 # MarkdownParser (tree-sitter), PlainTextParser
├── reader/                  # ReadOnlyContext for multiprocess mode
├── search/                  # Orchestrator (RRF fusion), Pipeline (dedup, MMR)
└── worker/                  # Worker process entry point and state

Read the full file on GitHub · 154 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 · 154 lines · 1,800 tokens per session scan A 6e8ef6cf83f3

Subscribe to this mod's changes

ragdocs-mcp copilot-instructions.md is an instructions file published in the GitHub repository andnp/ragdocs-mcp (2 stars, last pushed 6d ago), licensed MIT. It adds 1,800 tokens to every session, about $0.0090 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 2026-08-31.

Data and AIRAG and vectors
Related

Other instructions, from other repositories

GPT-RAG config-python.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…

Azure/GPT-RAG · 180 tokens

GPT-RAG release.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…

Azure/GPT-RAG · 207 tokens

pdf-brain AGENTS.md

Instructions for joelhooks/pdf-brain, covering pdf-brain agent notes, libsql quirks, ai sdk pattern, key files and docs.

joelhooks/pdf-brain · 531 tokens

rag-code-mcp copilot-instructions.md

Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.

doITmagic/rag-code-mcp · 568 tokens

gpt-rag-mcp AGENTS.md

Instructions for Azure/gpt-rag-mcp, covering gpt-rag mcp engineering-agent contract, priority, what this repository is, repository boundaries and how to work.

Azure/gpt-rag-mcp · 1,862 tokens

gemini-cli-extension GEMINI.md

Instructions for pinecone-io/gemini-cli-extension, covering pinecone extension for gemini cli, available agent skills, key concepts & setup and available mcp tools.

pinecone-io/gemini-cli-extension · 569 tokens