What is evoke CLAUDE.md?

A project guide for Evoke, an AI-powered platform that turns written app descriptions into web applications. It documents the project structure, development commands, architecture, database work, and build process.

Use it when developing, building, linting, or changing the database and code-generation workflow in the Evoke project.

Without the guide, an agent may not know how Evoke is organised or which commands and services are involved. It provides the repository-specific information needed to make and check changes.

How cheeseburgertony/evoke configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cheeseburgertony/evoke. 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/cheeseburgertony/evoke/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/cheeseburgertony/evoke

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/cheeseburgertony/evoke/claude-md/github.svg)](https://agentmods.dev/instructions/cheeseburgertony/evoke/claude-md)

Your own site

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

Per session 938 This file is loaded in full into every session.

When invoked 938 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 95% copy Near-identical to another mod 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	$0.00938	$0.00938
Opus 5.5	$0.00375	$0.00375
Sonnet 5.5	$0.00188	$0.00188
Haiku 4.5	$0.00094	$0.00094

Measured 2mo ago against content hash 358beeacd315, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evoke 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.

Origin

This is a copy

95% identical to evoke AGENTS.md — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 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

Evoke is an AI-powered code generation platform that transforms natural language descriptions into working web applications. Users describe what they want to build, and AI agents generate and execute Next.js code in sandboxed environments.

Development Commands

# Development
npm run dev          # Start Next.js dev server

# Build
npm run build        # Production build

# Linting
npm run lint         # Run ESLint

# Database
npx prisma generate  # Generate Prisma client (runs automatically postinstall)
npx prisma db push   # Push schema changes to database
npx prisma studio    # Open Prisma Studio GUI

Architecture

Core Flow

User describes app → tRPC mutation creates project + sends Inngest event
Inngest AI agent generates code using tools (terminal, createOrUpdateFiles, readFiles)
E2B sandbox executes code with hot reload
SSE streams real-time progress to frontend
Fragment saved with generated files and sandbox URL

Directory Structure

src/modules/ - Feature modules (home, messages, projects, usage). Each module has server/procedures.ts for tRPC routes and ui/ for React components
src/trpc/ - tRPC setup. init.ts defines context and auth middleware. Routers combined in routers/_app.ts
src/inngest/ - AI agent orchestration. functions.ts contains the main code generation agent with tools
src/lib/ - Utilities: ai-models.ts (model configs), sse-manager.ts (real-time updates), prisma.ts (db client)
src/components/ui/ - Shadcn/UI components (pre-installed, import from @/components/ui/*)
prisma/schema.prisma - Database models: Project, Message, Fragment, Usage

Key Patterns

tRPC Routers: Feature modules export routers that are merged in src/trpc/routers/_app.ts. Use protectedProcedure for authenticated routes.

AI Models: Configured in src/lib/ai-models.ts. Multiple providers (Silicon, DeepSeek, LongCat, etc.) via OpenAI-compatible APIs. Add new models to AIModelIdType and aiModels array.

Read the full file on GitHub · 78 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 · 78 lines · 938 tokens per session scan A 358beeacd315

Subscribe to this mod's changes

evoke CLAUDE.md is an instructions file published in the GitHub repository cheeseburgertony/evoke (159 stars, last pushed 5mo ago), licensed MIT. It adds 938 tokens to every session, about $0.0038 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to evoke AGENTS.md, differing in 4 lines, and is treated as a copy.

ai ai-agents ai-builder inngest-agent-kit nextjs

evoke CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
evoke CLAUDE.mdcheeseburgertony/evoke	Instructions file	159	5mo ago	MIT	A	938	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

evoke: Instructions file for Claude Code