vibing.nvim CLAUDE.md

vibing.nvim CLAUDE.md is an instructions file for coding agents from shabaraba/vibing.nvim. It costs 1,984 tokens per session, scanned A, original, MIT.

Repository instructions for a Neovim plugin that puts a Claude chat inside the editor by running an AI command-line tool and reading its streamed output.

In plain words
What is it for?
Developing or testing the Neovim chat plugin, its MCP server, command tools, Lua code, Node.js code, documentation, and optional Codex command-line support.
Why use it?
They document the project's architecture and the commands for building, testing, checking, linting, formatting, and validating documentation.

Instructions file

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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/shabaraba/vibing.nvim/claude-md
Clone the repo
git clone --depth 1 https://github.com/shabaraba/vibing.nvim

Wrote 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.

agentmods badge for vibing.nvim CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shabaraba/vibing.nvim/claude-md.svg)](https://agentmods.dev/instructions/shabaraba/vibing.nvim/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shabaraba/vibing.nvim/claude-md"><img src="https://agentmods.dev/badge/instructions/shabaraba/vibing.nvim/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,984 This file is loaded in full into every session.
When invoked 1,984 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 $0.01984 $0.01984
Opus 5 $0.00992 $0.00992
Sonnet 5 $0.00397 $0.00397
Haiku 4.5 $0.00198 $0.00198

Measured today against content hash 6bc4ad3cd004, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibing.nvim 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 today.

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.

CLAUDE.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 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

vibing.nvim is a Neovim plugin that provides a Claude chat inside Neovim by spawning the claude CLI directly (claude -p --output-format stream-json) and parsing its stream. There is no Node.js agent wrapper process; the Node side is only the MCP server and two hook scripts. A Codex CLI backend is also supported. See .claude/rules/architecture.md.

Commands

# Install dependencies
npm install

# Build the MCP server
./build.sh

# Run Lua tests (requires Neovim with plenary.nvim)
npm run test:lua

# Run Node.js tests (tests/**/*.test.mjs)
npm run test:node

# Run E2E tests
npm run test:e2e

# Run agent behavior evals (spends real tokens — see tests/evals/README.md)
npm run test:eval

# Validate Lua syntax
npm run check

# Verify doc/*.txt (helptags, 78-column limit, CONTENTS/tag agreement)
npm run check:doc

# Lint TypeScript/JavaScript
npm run lint

# Fix lint issues
npm run lint:fix

# Format code
npm run format

# Check formatting
npm run format:check

# Lint Markdown files
npm run lint:md

For Neovim testing, load the plugin and run :VibingChat.

Documentation Structure

Detailed documentation is organized in .claude/rules/:

File Contents
architecture.md 不変条件とモジュール地図。詳細は handbook/architecture/ に外出し(下表)
mcp-integration.md MCP tools, usage examples, setup instructions
permissions.md Permission system, granular rules, Tool Approval UI
self-development.md Guidelines for developing vibing.nvim with vibing.nvim
self-testing.md E2E testing procedures, 3-try auto-fix rule, test helper reference
features.md Auto-resume on usage limit, message timestamps, AskUserQuestion support
configuration.md Full configuration examples, window positions, daily summary
commands-reference.md User commands, slash commands
web-workflow.md Claude Code on the Web: SessionStart env setup, git push reqs

Read the full file on GitHub · 139 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. today Changed · +10 lines · +325 tokens per session 6bc4ad3cd004
  2. 4d ago First seen · 129 lines · 1,659 tokens per session scan A a61d0dda154d

Subscribe to this mod's changes

vibing.nvim CLAUDE.md is an instructions file published in the GitHub repository shabaraba/vibing.nvim (13 stars, last pushed today), licensed MIT. It adds 1,984 tokens to every session, about $0.0099 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.

Related

Other instructions, from other repositories

claude-chat-exporter CLAUDE.md

Instructions for agarwalvishal/claude-chat-exporter, covering claude.md, what this is, core design decision, how the export works and the install page & bookmarklet (docs/index.html).

agarwalvishal/claude-chat-exporter · 4,543 tokens

bear-notes-mcp CLAUDE.md

Claude Code instructions for vasylenko/bear-notes-mcp, covering project purpose, rules of absolute importance, core technical documentation for this project, source layout and additional technical context.

vasylenko/bear-notes-mcp · 1,025 tokens

bear-notes-mcp copilot-instructions.md

Copilot instructions for vasylenko/bear-notes-mcp, covering when performing a code review for a pr, review objective, review guidelines and when working on a new feature or an idea.

vasylenko/bear-notes-mcp · 279 tokens

memctx CLAUDE.md

Claude Code instructions for bbhunterpk-ux/memctx: Last session: Database Schema UI Coverage Analysis — COMPLETED Completed: Analyzed database schema to identify all stored fields, Audited ProjectDetail and SessionDetail UI components, Compared API queries against UI display logic Up next: Add token usage display to…

bbhunterpk-ux/memctx · 116 tokens

claude-code-plus CLAUDE.md

Instructions for touwaeriol/claude-code-plus, covering claude code plus - 架构说明, 📋 项目概述, 🏗️ 整体架构, 模块说明 and 🔧 cli 补丁系统.

touwaeriol/claude-code-plus · 8,578 tokens

claude-code-plus AGENTS.md

Instructions for touwaeriol/claude-code-plus, covering claude code plus - 架构说明, 📋 项目概述, 🏗️ 整体架构, 🔌 三种通信方式 and 2️⃣ idea 集成通信 (纯 http).

touwaeriol/claude-code-plus · 3,013 tokens