goals

Goals

Goals is an open-source plugin for Claude Code and Codex that helps an AI agent run long enough to actually finish your goal.

It builds on the native /goal loop instead of replacing it: the agent still does the work, while Goals adds the durable plan, the proof each step ran, the decisions, and a memory of how you like things done — the things a long run needs to be something you can trust, check, and pick back up. Everything it does lives in plain files you own.

Just say what you want — for example:

• "build me a weight-loss tracking app"
• "make a web app that resizes and tags my photos"
• "add login and payments to my site"
• "clean up and document this messy codebase"

What Goals does

• Thinks before it builds. It breaks your goal into smaller problems, writes down the assumptions it's relying on, weighs a few options (including doing nothing), and tries to break its own work to catch mistakes — and you can read that reasoning in plain English.
• Proves "done" instead of claiming it. A step is accepted only after its check actually runs and passes. A failed check points to the next fix instead of a vague retry.
• Explains every decision. "Which database should we use" comes with what it picked, whether it's easy to undo, and why it fits your goal.
• Learns how you decide. For simple, reversible choices it stops asking and decides the way you have before. The risky or hard-to-undo ones still come to you.
• Stops on your terms. Set a token budget and a finish condition, so a long run can't go forever or quietly run up a bill.
• Stays yours. The plan, decisions, proof, and history are plain files you can read, edit, and resume in a new session — or hand to a different agent.

Who it's for

Anyone using AI to get real work done:

• If you don't code — you describe the goal and approve decisions in plain English; your AI assistant does the heavy lifting, and Goals keeps it on track.
• If you do code — a durable, scriptable workflow layer that keeps long AI tasks on the rails, with evidence, gates, and a readable audit trail.

How it works

   you say the goal
         │
         ▼
   Goals breaks it into clear steps  ──▶   the AI agent does the next step
         ▲                                             │
         │            you say yes   ◀──── plain decision + proof it works
         └─────────  repeat until done — with a record of everything  ◀─┘

Goals runs the workflow; your AI assistant (Claude Code, Codex, …) does the work. Goals is the part that keeps it organized, legible, and accountable.

Under the hood it's a small CLI plus a plugin, working over plain files in your own project — so the goal, the decisions, and the proof are yours and survive a /clear or a brand-new session. The assess step follows PACERS, a method for solving problems without rushing.

Here's the whole loop, each step in plain English (click to enlarge):

And you never lose the thread: a dashboard anyone can read shows status, decisions, and proof at a glance (click to view full size):

_{Diagram source: docs/assets/lifecycle.mmd — regenerate with npx -y @mermaid-js/mermaid-cli -i docs/assets/lifecycle.mmd -o docs/assets/lifecycle.png -b white -s 2.}

See docs/architecture.md for the full set: system architecture, the goal lifecycle, skill-first discovery + capability gaps, and the portability layer that lets a goal survive /clear.

Get started

Claude Code

Two lines — that's the whole install:

/plugin marketplace add ShivamGupta42/goals
/plugin install goals@goals