#324324th of 324 in Skills, plugins and prompts
sudolang
Pseudocode language for writing structured prompts that LLMs interpret directly
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 1.4k
- License
- MIT
- Last commit
- Dec 2025
- Language
- TypeScript
1,316 on 3 Apr 20261,362 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
SudoLang is a pseudocode language for prompting LLMs, with interfaces, constraints, /commands, pattern matching and a |> function composition operator. Programs are plain text that models such as ChatGPT, Claude, Gemini and Llama interpret without a pasted spec. The repo holds the language documentation, examples and a VS Code/Cursor extension (.vsix) for highlighting .sudo, .sudo.md and .mdc files.
Who it is for: Prompt authors who want structured, program-like prompts for LLMs
Strengths
- Works across ChatGPT, Claude, Gemini and Llama without pasting a spec
- Includes a VS Code/Cursor extension with highlighting for .sudo, .sudo.md and .mdc
- Docs, examples folder and several articles and talks for learning
- MIT licensed; README claims 20-30% fewer tokens than equivalent natural-language prompts
Weaknesses
- No runtime or interpreter; behavior depends on how each model reads the prompt
- Token savings and reasoning gains are claims in the README, not benchmarked here
- Extension installs from a local .vsix after cloning, not from a marketplace
- No tagged releases; last commit 2025-12-23
What it needs
- no GPU
- Needs VS Code or Cursor (optional, for the extension)
- Models: ChatGPT, Bing Chat, Anthropic Claude, Google Gemini/Gemma, Meta Llama
Quick answers
Is sudolang open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |