explaingit

secemp9/goal

Analysis updated 2026-05-18

6ShellAudience · developerComplexity · 2/5LicenseSetup · moderate

TLDR

An MCP tool that gives Claude Code, Cursor, and OpenCode a persistent goal that auto-continues across turns until finished.

Mindmap

mindmap
  root((goal))
    What it does
      Persistent objective
      Auto continuation
      Turn budgets
    Tools
      create_goal
      get_goal
      update_goal
    Tech stack
      Bash
      Python MCP server
      JSON state file
    Use cases
      Long multi step refactors
      Writing a test suite
      Debugging without re-prompting
    Audience
      Claude Code users
      Cursor and OpenCode users

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Set a long-running objective so an AI coding agent keeps working across many turns without re-prompting.

USE CASE 2

Cap how many turns an agent can use on a task with an automatic wrap-up when the budget runs out.

USE CASE 3

Add auto-continuation hooks to Claude Code so refactors and test-writing tasks run to completion.

What is it built with?

ShellPythonMCPuv

How does it compare?

secemp9/goaljerlinn/jerlin-wereadjonluca/dotfiles
Stars666
LanguageShellShellShell
Last pushed2024-06-02
MaintenanceDormant
Setup difficultymoderateeasy
Complexity2/51/5
Audiencedeveloperdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Full experience requires uv, jq, and bash 4+, plus running install.sh to register hooks.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice (MIT license).

In plain English

Goal is a tool that gives AI coding assistants, such as Claude Code, Cursor, and OpenCode, a persistent memory of what they are trying to accomplish across multiple exchanges. Without it, an AI agent stops after one response and forgets the overarching objective, so you have to manually re-prompt it to keep going. Goal solves this by letting you declare an objective once, and the agent works toward it across many turns automatically. The tool installs as an MCP server, MCP being a standard way for AI tools to communicate with assistants. Once installed, it exposes three core actions: creating a goal, checking current status, and marking a goal complete. Goal state is stored as a JSON file per project, tracking the objective text, current status (active, paused, budget limited, or complete), turns used, and elapsed time. For Claude Code specifically, Goal also installs hooks, small scripts that fire at key moments in a session. One injects a goal reminder at the start of each turn. Another monitors turn usage and warns when approaching the budget limit. A third is the auto-continuation engine: after each turn ends, it checks whether the goal is still active and automatically starts another turn without you re-prompting. Other editors get the MCP tools but not auto-continuation, so they require manual prompting to continue. You would use this when you have a large, multi-step task, such as refactoring a module, writing a test suite, or debugging a complex issue, and want an AI assistant to keep working without constant hand-holding. Written in Shell, ported from the goal architecture in Codex CLI, and released under the MIT license.

Copy-paste prompts

Prompt 1
Install the goal MCP server into Claude Code and set a goal to refactor my auth module.
Prompt 2
Explain what happens when the turn budget I set for a goal runs out.
Prompt 3
Show me how to pause and resume a goal partway through a task.
Prompt 4
Set up the goal skill for OpenCode using the install.sh script.

Frequently asked questions

What is goal?

An MCP tool that gives Claude Code, Cursor, and OpenCode a persistent goal that auto-continues across turns until finished.

What language is goal written in?

Mainly Shell. The stack also includes Shell, Python, MCP.

What license does goal use?

Use freely for any purpose, including commercial use, as long as you keep the copyright notice (MIT license).

How hard is goal to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is goal for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.