superplan-md

superplan-md / superplan-plugin

Public

Superplan is a CLI-first workflow engine that turns unstructured work into a deterministic, task-driven execution system for humans and AI agents.

superplan.md agent-workflow ai-agents automation cli dev-tooling
15
0
69% credibility
Found Mar 24, 2026 at 15 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Superplan is a command-line tool that structures AI agent workflows in code repositories by tracking changes, tasks, and progress with a live desktop overlay.

How It Works

1
🔍 Discover Superplan

You hear about a simple tool that keeps AI helpers organized while working on code projects.

2
📥 Get it running

Paste one easy command to install it on your computer.

3
🏠 Prepare your project

Run a quick setup command in your code folder to get ready for tracked work.

4
📋 Start a new goal

Create a named area for your feature or fix with one command.

5
🎯 Map out the steps

List tasks in a clear plan so nothing slips through the cracks.

6
🤖 Agents take action

AI follows the plan, tackling one task at a time without wandering.

7
👁️ See it all live

A handy window pops up showing exactly what's next and progress.

✅ Work done right

Every task finishes structured, with full visibility and no lost details.

Sign up to see the full architecture

6 more

Sign Up Free

Star Growth

See how this repo grew from 15 to 15 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is superplan-plugin?

Superplan-plugin installs a CLI-first workflow engine that turns unstructured work into a deterministic, task-driven execution system for humans and AI agents. You run `superplan init` in a repo to get structured task graphs under `.superplan/changes/`, then use `superplan run --json` or `status --json` to drive execution loops with real progress tracking. Built in TypeScript, it pairs with a desktop overlay for live visibility into active tasks, blockers, and handoffs.

Why is it gaining traction?

It stands out by enforcing runtime truth over drifting plans—agents execute one task at a time via CLI, with durable state that survives handoffs, no chat memory required. The skills library (entry, route, shape, execute, review) composes phases without over-planning, and JSON-first commands keep agents in tight loops. Developers notice fewer "done?" ambiguities and resumable work.

Who should use this?

AI agent wranglers building repo workflows, especially those tired of vague planning chats turning into lost context. Teams doing brownfield changes or multi-step features where humans and agents alternate tasks. Cursor/Claude users wanting deterministic execution without custom scripting.

Verdict

Try it if you're prototyping agent-driven repos—innovative CLI-first approach shines for task-driven systems, but low maturity (15 stars, 0.699999988079071% credibility) means expect rough edges in docs and edge cases. Solid for early adopters; watch for stability as it grows.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.