promptbin CLAUDE.md

promptbin CLAUDE.md is an instructions file for coding agents from ianphil/promptbin. It costs 1,124 tokens per session, scanned A, original, MIT.

Project instructions for PromptBin, a locally run prompt-management service that provides both an MCP server and a web interface. MCP is a standard way for AI tools to connect to external services.

In plain words
What is it for?
Use them when working on PromptBin, including installing it from PyPI, starting its web or MCP modes, and setting up development.
Why use it?
They explain how to install, run, develop, and verify PromptBin without having to infer its commands or operating modes.

Instructions file

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/ianphil/promptbin/claude-md
Clone the repo
git clone --depth 1 https://github.com/ianphil/promptbin

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 promptbin CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ianphil/promptbin/claude-md.svg)](https://agentmods.dev/instructions/ianphil/promptbin/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ianphil/promptbin/claude-md"><img src="https://agentmods.dev/badge/instructions/ianphil/promptbin/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,124 This file is loaded in full into every session.
When invoked 1,124 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 $0.01124 $0.01124
Opus 5 $0.00562 $0.00562
Sonnet 5 $0.00225 $0.00225
Haiku 4.5 $0.00112 $0.00112

Measured 4d ago against content hash 695fb0a79de6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

promptbin 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 4d 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 · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 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

PromptBin is the easiest way to run a Model Context Protocol (MCP) server with full prompt management capabilities. It's designed as a reference implementation and example for MCP server integration.

Primary use case: uv add promptbin && uv run promptbin

Modes:

  • Both Mode (default): MCP server + auto-launching web interface
  • MCP Server Mode: MCP protocol only with --mcp flag
  • Web Mode: Web interface only with --web flag

Development Commands

For PyPI distribution (recommended):

# Install from PyPI
uv add promptbin

# Run both MCP server + web interface (primary use case)
uv run promptbin

# Run only MCP server
uv run promptbin --mcp

# Run only web interface
uv run promptbin --web

# Setup verification
uv run promptbin-setup

# Install Dev Tunnels CLI
uv run promptbin-install-tunnel

For development:

# Clone and develop
git clone https://github.com/ianphil/promptbin
cd promptbin
uv sync
uv run promptbin

Architecture Overview

Core Components

  • Flask Web App (app.py): HTMX-powered interface on localhost:5000
  • MCP Server (mcp_server.py): Model Context Protocol integration with auto-lifecycle management
  • File-Based Storage: JSON files in ~/promptbin-data/{category}/{prompt_id}.json
  • Microsoft Dev Tunnels: Secure sharing with automatic security protections

Data Organization

~/promptbin-data/
├── coding/     # Development-related prompts
├── writing/    # Content creation prompts  
├── analysis/   # Data analysis prompts
└── shares.json # Share token management

Key Design Principles

  • Local-First: All data stored locally by default
  • Zero Database: File-based storage only
  • HTMX Integration: No full page reloads, dynamic interactions
  • Security by Design: Rate limiting (5 attempts per IP kills tunnel)
  • Template Variables: Support for {{variable}} syntax with special highlighting

Read the full file on GitHub · 135 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. 4d ago First seen · 135 lines · 1,124 tokens per session scan A 695fb0a79de6

Subscribe to this mod's changes

promptbin CLAUDE.md is an instructions file published in the GitHub repository ianphil/promptbin (0 stars, last pushed 8mo ago), licensed MIT. It adds 1,124 tokens to every session, about $0.0056 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.