agentmods.dev

vibeyard: Instructions file for Claude Code

CLAUDE.md

vibeyard CLAUDE.md is an instructions file for Claude Code from elirantutia/vibeyard. It costs 8,815 tokens per session, scanned A, original, MIT.

A repository instruction file for Vibeyard, a desktop terminal application built with Electron. It explains how to build, run and test the app, which uses terminal sessions rendered in a desktop interface.

In plain words
What is it for?
Use it when developing Vibeyard's Electron main process, preload layer, renderer, terminal sessions or cross-platform packaging. It covers Node.js requirements, Vitest tests and build commands.
Why use it?
It gives a coding agent the project-specific commands, runtime requirements and architecture it needs before making changes. It also records the lack of hot reload and the need to rebuild and restart after edits.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is elirantutia/vibeyard's own configuration. It tells Claude Code how to work on vibeyard 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 vibeyard configures →

not rated 1.4krepo +9 changed 6d ago A scan 8,815 tokens original MIT
View source ↗ elirantutia/vibeyard
About the project

Vibeyard is an IDE and project workspace for managing multiple AI coding-agent sessions, including parallel runs, split panes, task boards, cost tracking, and session resumption. It is for developers who use Claude Code, Codex CLI, or Gemini CLI and need to organize many agent-driven coding tasks. The catalogue add-ons provide commands, skills, and instructions for working with Vibeyard.

elirantutia/vibeyard · 1,369 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to elirantutia/vibeyard. 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/elirantutia/vibeyard/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/elirantutia/vibeyard

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 vibeyard CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/elirantutia/vibeyard/claude-md"><img src="https://agentmods.dev/badge/instructions/elirantutia/vibeyard/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,815 This file is loaded in full into every session.
When invoked 8,815 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.08815 $0.08815
Opus 5 $0.04408 $0.04408
Sonnet 5 $0.01763 $0.01763
Haiku 4.5 $0.00881 $0.00881

Measured 6d ago against content hash 61e4906d2992, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vibeyard CLAUDE.md scanned grade A with 1 finding 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 6d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

Three renderer modules (`session-cost.ts`, `session-activity.ts`, `session-context.ts`) expose `_resetForTesting()` to clear module-level state between tests. Main process tests mock `fs`, `child_process`, `node-pty`, an
CLAUDE.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 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.

What This Is

A terminal-centric IDE desktop app built on Electron that wraps CLI tool sessions. Users manage projects and sessions, each backed by a PTY running a CLI tool (currently Claude Code, with an abstraction layer for future providers like Copilot CLI and Gemini CLI), rendered via xterm.js.

Build & Run

npm run build    # Compile all three targets (main, preload, renderer) + copy assets
npm start        # Build then launch Electron app (alias: npm run dev)

No hot reload — changes require rebuild + app restart.

Requires Node v24 (see .nvmrc). No lint tooling is configured.

Cross-platform: builds and runs on macOS, Linux, and Windows. Release artifacts (via electron-builder) include .dmg/.zip (mac), .deb/.AppImage (linux), and NSIS installer + portable .exe (win). CI covers all three platforms.

Testing

npm test             # Run all tests once
npm run test:watch   # Watch mode (re-runs on file changes)
npm run test:coverage # Run with coverage report (terminal + HTML)

Uses Vitest with v8 coverage. Tests are co-located with source files as *.test.ts. Coverage HTML report outputs to coverage/index.html.

Test files are excluded from production builds via exclude in tsconfig.main.json and tsconfig.renderer.json.

Three renderer modules (session-cost.ts, session-activity.ts, session-context.ts) expose _resetForTesting() to clear module-level state between tests. Main process tests mock fs, child_process, node-pty, and os via vi.mock().

Architecture

Three-process Electron architecture with strict context isolation:

  • Main process (src/main/) — Node.js side: window creation, PTY lifecycle via node-pty, filesystem access, persistent state (~/.vibeyard/state.json). IPC handlers in ipc-handlers.ts dispatch to pty-manager.ts and store.ts. CLI tool behavior is abstracted via the provider system (src/main/providers/).
  • Preload (src/preload/preload.ts) — Secure bridge exposing window.vibeyard API via contextBridge with namespaces: pty, session, store, profiles, fs, provider, menu.
  • Renderer (src/renderer/) — Vanilla TypeScript DOM UI (no framework). AppState singleton in state.ts uses an event emitter pattern; components in components/ subscribe to state changes.

Read the full file on GitHub · 157 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. 6d ago Changed · +1 lines · +874 tokens per session 61e4906d2992
  2. 8d ago Changed · +1 lines · +456 tokens per session bc40ae7e6d6b
  3. 10d ago First seen · 155 lines · 7,485 tokens per session scan A a4c204b2fe07

Subscribe to this mod's changes

vibeyard CLAUDE.md is an instructions file published in the GitHub repository elirantutia/vibeyard (1,369 stars, last pushed 7d ago), licensed MIT. It adds 8,815 tokens to every session, about $0.0441 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodePlanningTestingccclideveloper-toolside
Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens