AI Agent Hub
Back to plugins
🧩

xby-random-number

admin-security Updated 2026.09.02

Run the following command in DeepSeek Harness:

dsh plugin install xby-skill/xby-random-number

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install xby-skill/xby-random-number in the DeepSeek Harness terminal to install this plugin; the repository is at https://github.com/xby-skill/xby-random-number.

About this plugin

Inside a DeepSeek Harness session, pulling a throwaway test parameter, minting a cryptographically secure one-time token, or making a weighted draw from a candidate list are small but frequent tasks that previously required leaving the chat, opening a terminal, and writing a few lines of Python. xby-random-number folds all of that into the conversation itself, so a single natural-language instruction is enough to get the result without switching context.

The plugin spans two tiers of randomness. On the pseudo-random side it offers bounded integers (inclusive on both ends), bounded floats, draw-with-replacement with optional per-item weights, list shuffling, and draw-without-replacement sampling — all with a parameter style close to the Python standard library so the learning curve is essentially zero. On the cryptographically secure side it taps the operating-system entropy source to produce hex-formatted tokens (32 bytes by default, length configurable) and range-limited secure random integers, making it a natural fit for session keys, one-time credentials, or safety tags. A persisted API-key setter is also included, so credentials survive restarts without re-entry.

If you are building automated workflows in DSH, generating test parameters on the fly, sampling datasets randomly, or simply want a drop-in way to produce a cryptographically random value mid-conversation, xby-random-number is a lightweight, plug-and-play choice that requires no extra scripts, configuration files, or external tooling.

Use Cases

  • Generate random integers or floats for test parameters directly inside a DeepSeek Harness session
  • Mint cryptographically secure one-time tokens, session keys, or temporary credentials
  • Perform weighted random draws or without-replacement sampling from a candidate list
  • Inject unpredictable random parameters into downstream steps of an automated workflow

Best For

  • Developers building DSH-powered workflows who need a quick random value mid-conversation
  • Engineers with security requirements who must derive tokens or keys from OS entropy sources
  • Researchers performing random sampling for data analysis or A/B testing pipelines