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.
npx agentmods add instructions/linw1995/nvim-mcp/claude-mdgit clone --depth 1 https://github.com/linw1995/nvim-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/linw1995/nvim-mcp/claude-md)<a href="https://agentmods.dev/instructions/linw1995/nvim-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/linw1995/nvim-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00787 | $0.00787 |
| Opus 5 | $0.00394 | $0.00394 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
nvim-mcp CLAUDE.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is a Rust-based MCP (Model Context Protocol) server that provides seamless integration with Neovim instances. The server acts as a bridge between AI assistants and Neovim editors, enabling operations like LSP integration, diagnostic analysis, and file manipulation through structured MCP tools and resources.
Development Commands
More details in @./docs/development.md .
Building and Running
# Development build and run
cargo build
cargo run -- --connect auto
# Connect to specific targets
cargo run -- --connect 127.0.0.1:6666
cargo run -- --connect /tmp/nvim.sock
# HTTP server mode with auto-connection
cargo run -- --http-port 8080 --connect auto
# Production build
cargo build --release
Testing
# Run all tests with output
./scripts/run-test.sh -- --show-output
# Run specific test modules
./scripts/run-test.sh -- --show-output neovim::integration_tests
# Skip integration tests (which require Neovim)
./scripts/run-test.sh -- --skip=integration_tests --show-output
# Run tests with coverage
./scripts/run-cov.sh -- --show-output
Linting and Formatting
pre-commit run --all-files
Architecture Overview
Core Components
- MCP Server Core (
src/server/core.rs): Main server implementation with connection management using DashMap for thread-safe concurrent access - Neovim Client (
src/neovim/client.rs): Handles communication with Neovim instances via nvim-rs msgpack-rpc - Tool System (
src/server/tools.rs): 26+ MCP tools for LSP operations, file navigation, and diagnostics - Resource System (
src/server/resources.rs): Connection-scoped diagnostic resources with URI schemes - Transport Layer: Supports both stdio and HTTP server transports via rmcp
Testing Architecture
- Integration Tests: Full MCP client-server communication tests in
src/server/integration_tests.rsandsrc/neovim/integration_tests.rs - LSP Testing: Comprehensive Go/gopls integration with test data in
src/testdata/ - Global Test Mutex: Prevents port conflicts during concurrent execution
- Automated Setup: Tests spawn and manage Neovim instances automatically
- Code Coverage: LLVM-based coverage using grcov with HTML/Cobertura/Markdown reports
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.
- 4d ago First seen · 108 lines · 787 tokens per session scan A 2684491c8d6a
nvim-mcp CLAUDE.md is an instructions file published in the GitHub repository linw1995/nvim-mcp (67 stars, last pushed 2d ago), licensed Apache-2.0. It adds 787 tokens to every session, about $0.0039 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.
Other instructions, from other repositories
sidekick.nvim AGENTS.md
Instructions for folke/sidekick.nvim, covering agent cheat sheet, project overview, everyday commands, adding features and writing tests.
cclsp CLAUDE.md
Instructions for ktnyt/cclsp, covering claude.md, project overview, development commands, install dependencies and development with hot reload.
chromia-lsp-mcp CLAUDE.md
Claude Code instructions for ChromiaProject/chromia-lsp-mcp, covering claude.md, what this is, commands, architecture and adding a tool.
claude-cli.nvim CLAUDE.md
Instructions for edo1z/claude-cli.nvim, covering claude code multi-instance manager 開発ガイド, 重要事項, 開発プロセス, テスト方針 and コーディング規約.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).