What is vibedoc CLAUDE.md?

A Next.js application that shows developer tasks and documentation, while also providing an MCP server for AI coding agents. It reads Markdown files from a project and uses the same API for the web interface and agents.

It is for browsing project documents, managing tasks, reading or updating MEMORY.md, creating architecture decision records, and connecting an AI agent through an HTTP endpoint.

It gives developers and coding agents one place to view tasks, search documentation, record decisions, and share project memory without a separate database.

How quanghoangf/vibedoc configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to quanghoangf/vibedoc. 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/quanghoangf/vibedoc/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/quanghoangf/vibedoc

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/quanghoangf/vibedoc/claude-md/github.svg)](https://agentmods.dev/instructions/quanghoangf/vibedoc/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/quanghoangf/vibedoc/claude-md"><img src="https://agentmods.dev/badge/instructions/quanghoangf/vibedoc/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/quanghoangf/vibedoc/claude-md"><img src="https://agentmods.dev/badge/instructions/quanghoangf/vibedoc/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 834 This file is loaded in full into every session.

When invoked 834 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.

Model	Per session	Once invoked
Fable 5.1	$0.00834	$0.00834
Opus 5	$0.00417	$0.00417
Sonnet 5	$0.00167	$0.00167
Haiku 4.5	$0.00083	$0.00083

Measured 9d ago against content hash dee93e41c996, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

vibedoc 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 9d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibeDoc — Agent Instructions

What this is

A Next.js 14 app that serves as both a kanban/docs viewer for developers AND an MCP server for AI coding agents. One running process, two clients. The UI and the AI agent share the same API layer.

Stack

Framework: Next.js 14 (App Router, TypeScript)
Styling: Tailwind CSS — dark theme, no component library
Runtime: Node.js 18+ (server-side file system access)
MCP transport: HTTP JSON-RPC 2.0 at /api/mcp
Real-time: Server-Sent Events at /api/events
Data: File system only — no database. Reads .md files from target project.

Repo structure

src/
  app/
    page.tsx              ← Main UI shell (single-page, client component)
    layout.tsx            ← Root layout
    globals.css           ← Tailwind + markdown prose styles
    api/
      mcp/route.ts        ← MCP JSON-RPC endpoint (AI connects here)
      events/route.ts     ← SSE stream (real-time browser updates)
      tasks/route.ts      ← Task CRUD
      docs/route.ts       ← Doc list/read/search
      memory/route.ts     ← MEMORY.md read/write
      decisions/route.ts  ← ADR creation
      activity/route.ts   ← Activity log read
      projects/route.ts   ← Multi-project discovery
      summary/route.ts    ← Combined project status
  lib/
    core.ts               ← ALL file system logic (shared by API routes + MCP)
    events.ts             ← In-process SSE event bus (singleton)
docs/                     ← VibeDoc's own documentation (this project)
plans/tasks/              ← Development tasks
memory/MEMORY.md          ← Session handoff

Commands

npm install               # install deps
npm run dev               # start dev server → http://localhost:3000
npm run build             # production build
npm run lint              # lint

# Point at a target project:
VIBEDOC_ROOT=/path/to/project npm run dev

Key architecture rules

src/lib/core.ts is the only place that touches the file system. API routes import from core, never use fs directly.
src/lib/events.ts is the only SSE bus. Call emitUpdate() from API routes after mutations — never from core.ts.
page.tsx is a single client component. All data fetching is via fetch() to our own API routes. No server components in the main UI (real-time state management requires client).
/api/mcp is hand-rolled JSON-RPC. Do NOT introduce the MCP SDK stdio transport — it doesn't work in Next.js API routes. Stay with the HTTP JSON-RPC approach.
No database. All state lives in the target project's files. .vibedoc-activity.json is the only file VibeDoc writes to the project (besides task status and MEMORY.md).

Read the full file on GitHub · 75 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.

9d ago First seen · 75 lines · 834 tokens per session scan A dee93e41c996

Subscribe to this mod's changes

vibedoc CLAUDE.md is an instructions file published in the GitHub repository quanghoangf/vibedoc (5 stars, last pushed 4mo ago), licensed MIT. It adds 834 tokens to every session, about $0.0042 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.

Frontend Writing and docs

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

vibedoc: Instructions file for Claude Code