Borrowing it
Nothing to install: this file belongs to santanusinha/neovim-use-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/santanusinha/neovim-use-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/santanusinha/neovim-use-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/santanusinha/neovim-use-mcp/agents-md)<a href="https://agentmods.dev/instructions/santanusinha/neovim-use-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/santanusinha/neovim-use-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/santanusinha/neovim-use-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/santanusinha/neovim-use-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00561 | $0.00561 |
| Opus 5 | $0.00280 | $0.00280 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
neovim-use-mcp AGENTS.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 10d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for agents that work on this repository.
What this is
An MCP server (TypeScript, stdio) that drives a headless Neovim process, so an AI agent can edit files with the user's LSP, formatters and plugins.
Layout
| Path | Role |
|---|---|
src/index.ts |
Entry point: stdio transport, tool registration, shutdown |
src/nvim/session.ts |
Spawns or attaches nvim, serialises calls, warms plugins |
src/nvim/lua.ts |
Every Lua chunk that runs inside nvim |
src/tools/buffer.ts |
File and buffer tools |
src/tools/lsp.ts |
LSP tools |
src/tools/exec.ts |
Lua and Ex command escape hatches |
src/tools/context.ts |
Shared helpers: open, save, diagnostics feedback |
src/util/ |
Config, errors, output format |
test/ |
Vitest suite plus manual smoke scripts |
Rules
- Never write to stdout. It carries the MCP protocol. Log to stderr.
- Put all Lua in
src/nvim/lua.ts. Do not inline Lua in tool files. - A Lua chunk reports a problem with
return { error = "..." }. The caller maps that to aToolErrorwith a hint. - Neovim sends absent arguments as
vim.NIL, notnil. Convert them at the top of the chunk. - Every edit tool saves by default and returns fresh diagnostics.
- Every tool gets
annotationswith the correct read-only and destructive hints. - Error messages must tell the agent what to do next.
Commands
npm run build # tsc
npm test # vitest, needs a real nvim
node test/smoke.mjs # buffer tools against a temp file
node test/lsp-go.mjs <dir> <file> # LSP tools against a project
Known constraints
- Headless nvim does not fire
UIEnterorVeryLazy.WARMUPinsrc/nvim/lua.tsforces lazy.nvim to load the LSP plugins. - Language servers attach at different speeds.
OPEN_FILEwaits for a stable client count instead of the first client. - One nvim process serves every request, so
NvimSession.runkeeps a queue.
Style
Write comments and documents in ASD-STE100 Simplified Technical English: short active sentences, simple words, no jargon.
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.
- 10d ago First seen · 58 lines · 561 tokens per session scan A be35f098e653
neovim-use-mcp AGENTS.md is an instructions file published in the GitHub repository santanusinha/neovim-use-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 561 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.