What is ditch-vercel CLAUDE.md?

A set of instructions for an AI coding agent working on ditch-vercel, a tool that helps move web apps from Vercel to other hosting platforms.

It helps an agent understand and contribute to the ditch-vercel repository across tools such as Claude Code, Cursor, Copilot, Codex, and Windsurf.

It gives the agent the project's purpose, structure, contribution rules, and commit-message guidance in one place.

How umarmuhandis/ditch-vercel configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to umarmuhandis/ditch-vercel. 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/umarmuhandis/ditch-vercel/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/umarmuhandis/ditch-vercel

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/umarmuhandis/ditch-vercel/claude-md/github.svg)](https://agentmods.dev/instructions/umarmuhandis/ditch-vercel/claude-md)

Your own site

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

Per session 921 This file is loaded in full into every session.

When invoked 921 The same file — it is already loaded in full.

Security scan C 2 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	$0.00921	$0.00921
Opus 5.5	$0.00368	$0.00368
Sonnet 5.5	$0.00184	$0.00184
Haiku 4.5	$0.00092	$0.00092

Measured 2mo ago against content hash d586115bc4a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

ditch-vercel CLAUDE.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

3. **Bash installer** — `curl -fsSL .../install.sh | bash`, zero dependencies

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. **Bash installer** — `curl -fsSL .../install.sh | bash`, zero dependencies

CLAUDE.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 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

An agent skill that automates migrating web apps from Vercel to other platforms. Installable as a Claude Code plugin (claude plugin marketplace add umarmuhandis/ditch-vercel && claude plugin install ditch-vercel), via bash installer, or through AGENTS.md discovery. Works with Claude Code, Cursor, GitHub Copilot, Codex, Windsurf, and other AI coding agents. No build system, no tests, no compiled code — the entire skill is markdown-based knowledge files that agents follow as instructions.

Architecture

AGENTS.md                       → Universal agent discovery (Linux Foundation standard)
install.sh                      → Zero-dependency bash installer (agent detection + downloads)
adapters/
  cursor.mdc                    → Cursor adapter (thin pointer to SKILL.md)
  windsurf.md                   → Windsurf adapter
  clinerules.md                 → Cline/Roo adapter
.claude-plugin/plugin.json      → Plugin metadata (name, version, description)
.claude-plugin/marketplace.json → Claude Code plugin marketplace metadata
skills/ditch-vercel/
  SKILL.md                      → Orchestrator: 5-phase flow (scan → report → plan+approve → execute → done)
  frameworks/<name>.md          → Per-framework migration knowledge (6 files)
  targets/<name>.md             → Per-target-platform knowledge (cloudflare.md, vps.md)

Distribution channels (Vercel-independent):

Claude Code plugin — claude plugin marketplace add umarmuhandis/ditch-vercel && claude plugin install ditch-vercel
AGENTS.md — universal agent discovery, supported by 20+ agents
Bash installer — curl -fsSL .../install.sh | bash, zero dependencies
npx skills (legacy) — Vercel Labs dependency, kept for backwards compat

SKILL.md is the canonical entry point. It defines a 5-phase flow: scan (detect framework + Vercel features + target) → report (complexity scoring with GREEN/YELLOW/RED traffic light) → plan+approve (hard gate) → execute (with git safety checkpoint, task-driven progress via TaskCreate/TaskUpdate, and auto build verification) → done (summary + undo instructions). Framework and target files are referenced from SKILL.md and read during execution.

Read the full file on GitHub · 61 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.

2mo ago First seen · 61 lines · 921 tokens per session scan C d586115bc4a7

Subscribe to this mod's changes

ditch-vercel CLAUDE.md is an instructions file published in the GitHub repository umarmuhandis/ditch-vercel (5 stars, last pushed 8mo ago), licensed MIT. It adds 921 tokens to every session, about $0.0037 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

ditch-vercel CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ditch-vercel CLAUDE.mdumarmuhandis/ditch-vercel	Instructions file	5	8mo ago	MIT	C	921	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ditch-vercel: Instructions file for Claude Code