agentmods.dev

cldcde CLAUDE.md

cldcde CLAUDE.md is an instructions file for coding agents from aegntic/cldcde. It costs 605 tokens per session, scanned A, original, MIT.

Repository instructions for cldcde, a Bun-based web application with a Hono backend, JWT login, and a Neo4j graph database. Neo4j stores connected data such as users, extensions, and integrations as relationships.

In plain words
What is it for?
Use them when starting development, building or testing the app, configuring Neo4j, changing API routes, or working on login and resource-management features.
Why use it?
They explain the commands, database setup, authentication design, API layout, and validation rules needed to work on the project without guessing.

Instructions file

not rated 11 8d ago A scan 605 tokens original MIT
View the source file aegntic/cldcde
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/aegntic/cldcde/claude-md
Clone the repo
git clone --depth 1 https://github.com/aegntic/cldcde

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 cldcde CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aegntic/cldcde/claude-md.svg)](https://agentmods.dev/instructions/aegntic/cldcde/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/aegntic/cldcde/claude-md"><img src="https://agentmods.dev/badge/instructions/aegntic/cldcde/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 605 This file is loaded in full into every session.
When invoked 605 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00605 $0.00605
Opus 5 $0.00302 $0.00302
Sonnet 5 $0.00121 $0.00121
Haiku 4.5 $0.00060 $0.00060

Measured 5d ago against content hash c90d72581966, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cldcde 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 5d 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 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.

Commands

Development

  • bun dev - Start development server with hot reload
  • bun build - Build frontend for production
  • bun start - Run production server
  • bun test - Run tests (no tests implemented yet)

Database

  • Neo4j must be running locally or configured via environment variables
  • Database initialization: Create constraints and sample data by running queries in src/db/neo4j.ts

Architecture

Backend Structure

The backend uses Hono framework on Bun runtime with a modular API design:

  • API Routes (src/api/): Each module exports route handlers

    • Auth endpoints handle JWT-based authentication
    • Extensions and MCP endpoints manage platform resources
    • All routes use Zod for validation

  • Database (src/db/neo4j.ts): Neo4j graph database

    • Graph model: Users -> Extensions/MCPs with relationships (CREATED, INSTALLED, RATED)
    • Connection pool management with graceful fallback
    • Cypher queries for all database operations

  • Authentication (src/auth/): JWT tokens with bcrypt password hashing

    • Middleware in server.ts protects routes
    • Token verification for protected endpoints

Frontend Structure

React application with terminal-inspired UI:

  • Components (frontend/src/components/): Modular React components

    • Theme-aware components using styled-components
    • Terminal aesthetic with ASCII art and monospace fonts

  • Theming (frontend/src/styles/themes.ts): Multiple terminal themes

    • Theme context provider for global theme management
    • Themes: Default, Dracula, Monokai, Solarized, Nord, Gruvbox

  • State Management: React Context API for auth and theme state

Key Technical Decisions

  1. Bun over Node.js: Faster runtime with built-in TypeScript support
  2. Hono over Express: Lightweight, edge-ready framework
  3. Neo4j over SQL: Graph relationships perfect for user-extension connections
  4. styled-components: Dynamic theming with CSS-in-JS
  5. Zod validation: Type-safe runtime validation for APIs

Read the full file on GitHub · 67 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. 5d ago First seen · 67 lines · 605 tokens per session scan A c90d72581966

Subscribe to this mod's changes

cldcde CLAUDE.md is an instructions file published in the GitHub repository aegntic/cldcde (11 stars, last pushed 8d ago), licensed MIT. It adds 605 tokens to every session, about $0.0030 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 2026-08-30.

bunclaude-codecloudflare-workersextensionshonomcp
Related

Other instructions, from other repositories

pi-coding-agent-forge AGENTS.md

AGENTS.md instructions for Firstp1ck/pi-coding-agent-forge, covering repository documentation rules, documentation goal, required documentation layers, readme.md — human guide and technical.md — advanced user reference.

Firstp1ck/pi-coding-agent-forge · 2,075 tokens

nutrition-mcp CLAUDE.md

Claude Code instructions for akutishevsky/nutrition-mcp, covering claude.md, project overview, deploying, publishing to the registry and commands.

akutishevsky/nutrition-mcp · 11,933 tokens

projektor AGENTS.md

AGENTS.md instructions for TAJD/projektor, covering agents.md, what projektor is, coordination model (read this first), planning and design docs live in the wiki, not the repo and architecture: the service-layer contract (most important).

TAJD/projektor · 7,554 tokens

Ornn CLAUDE.md

Claude Code instructions for ChronoAIProject/Ornn, covering claude.md — chrono-ornn, product positioning, tech stack, architecture and code standards.

ChronoAIProject/Ornn · 6,198 tokens

munkel CLAUDE.md

Claude Code instructions for limehq/munkel, covering claude.md, monorepo layout, commands, macos development specifics and deploy.

limehq/munkel · 2,131 tokens

rewind AGENTS.md

AGENTS.md instructions for pdugan20/rewind, covering rewind, work modes, development commands, agent configuration and architecture overview.

pdugan20/rewind · 2,280 tokens