vibe-rules: Instructions file for Claude Code

CLAUDE.md

vibe-rules CLAUDE.md is an instructions file for Claude Code from Timelk/vibe-rules. It costs 1,835 tokens per session, scanned A, original, MIT.

Repository instructions for Vibe Rules, a Visual Studio Code extension that manages and synchronizes AI-agent skill files across multiple coding agents.

In plain words
What is it for?
They help with the dashboard, agent detection, skill scanning, cross-agent synchronization, difference checking, history, and remote skill management.
Why use it?
They give an agent an overview of the extension's services and data flow before it changes the code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions Codex; built for cline.

This is Timelk/vibe-rules's own configuration. It tells Claude Code how to work on vibe-rules itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vibe-rules configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Timelk/vibe-rules. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Timelk/vibe-rules/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Timelk/vibe-rules

Made for: Claude Code.

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 vibe-rules CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/timelk/vibe-rules/claude-md/github.svg)](https://agentmods.dev/instructions/timelk/vibe-rules/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/timelk/vibe-rules/claude-md"><img src="https://agentmods.dev/badge/instructions/timelk/vibe-rules/claude-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.

agentmods 80×15 button for vibe-rules CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/timelk/vibe-rules/claude-md"><img src="https://agentmods.dev/badge/instructions/timelk/vibe-rules/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,835 This file is loaded in full into every session.
When invoked 1,835 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01835 $0.01835
Opus 5.5 $0.00734 $0.00734
Sonnet 5.5 $0.00367 $0.00367
Haiku 4.5 $0.00184 $0.00184

Measured 2mo ago against content hash b879b99565e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vibe-rules 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 2mo 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.

CLAUDE.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vibe Rules - AI Context

Project Overview

Vibe Rules is a VSCode extension that manages and syncs AI coding agent skills (SKILL.md files) across 18 agents. It provides a Webview dashboard (Vite + React) opened as an editor tab, with local skill management, cross-agent sync, and remote skill marketplace integration.

Architecture

src/
├── extension/              # VSCode Extension Host (Node.js, TypeScript)
│   ├── extension.ts        # Entry: activate/deactivate, registers 3 commands
│   ├── providers/
│   │   └── DashboardViewProvider.ts  # WebviewPanel manager, message handler (17 cases)
│   │                                 # Also handles remote skill install/remove/search
│   ├── services/
│   │   ├── agent-detector.ts   # Detects installed agents, reads VSCode settings overrides
│   │   ├── skill-scanner.ts    # Scans SKILL.md files, gray-matter parsing, dedup by name
│   │   ├── sync-engine.ts      # Copy-based sync (snapshot → parallel write), source-safe
│   │   ├── diff-engine.ts      # Compares skill content across agents (canonical-first lookup)
│   │   ├── sync-history.ts     # Persistent sync log (~/.vibe-rules/sync-history.json, max 100)
│   │   ├── mcp-scanner.ts      # MCP config discovery (5 known locations)
│   │   └── file-watcher.ts     # SKILL.md change detection via FileSystemWatcher
│   └── types/
│       ├── agent.ts            # AgentConfig, AGENT_REGISTRY (18 agents)
│       ├── skill.ts            # Skill, SkillFrontmatter, SyncResult, SyncReport
│       └── messages.ts         # Extension <-> Webview message protocol (full type union)
└── webview/                # Vite + React (Tailwind CSS)
    ├── App.tsx             # Root state orchestrator (~595 lines, all top-level state)
    ├── components/
    │   ├── layout/         # Header, Sidebar, MainContent, RightPanel
    │   ├── skill/          # SkillList, SkillDetail, SyncDialog, CreateSkillDialog,
    │   │                     DiffPreview, SyncHistory, RemoteSkillPanel
    │   ├── agent/          # AgentTabs, AgentStatusBadge
    │   ├── mcp/            # McpList
    │   ├── settings/       # SettingsPanel
    │   └── common/         # SearchInput, ScopeToggle, ConfirmDialog, ResizeHandle
    ├── hooks/              # useSkills, useAgents, useVSCodeApi
    └── services/
        ├── vscode-message.ts      # postMessage bridge
        └── remote-skill-api.ts    # Remote source definitions + request helpers

Read the full file on GitHub · 141 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. 2mo ago First seen · 141 lines · 1,835 tokens per session scan A b879b99565e3

Subscribe to this mod's changes

vibe-rules CLAUDE.md is an instructions file published in the GitHub repository Timelk/vibe-rules (5 stars, last pushed 7mo ago), licensed MIT. It adds 1,835 tokens to every session, about $0.0073 per session on Opus 5.5. 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.

Related

vibe-rules CLAUDE.md compared with instructions from other repositories

vibe-rules CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vibe-rules CLAUDE.mdTimelk/vibe-rulesInstructions file57mo agoMITA1,835Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot