# Goal Loop

Draft /goal prompts and explain persistent agent loops.

- Repository: https://github.com/davidondrej/skills (4238 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add davidondrej/skills --skill goal-loop -g -a claude-code -y`
Codex: `npx skills add davidondrej/skills --skill goal-loop -g -a codex -y`
Cursor: `npx skills add davidondrej/skills --skill goal-loop -g -a cursor -y`
Gemini CLI: `npx skills add davidondrej/skills --skill goal-loop -g -a gemini-cli -y`

## Description

Draft /goal prompts and explain persistent agent loops. Use for goal or Ralph loops, autonomous run setup, monitoring, and troubleshooting.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Agent `/goal` Loop

## What `/goal` is

`/goal` makes an agent persist through `plan → act → test → review → iterate`.
If a turn ends before the goal is met, it auto-continues instead of waiting for
input. The loop ends at its stop condition, a user pause, or the token budget
limit. It is also called the “Ralph loop”.

Before giving runtime instructions, check goal support in the installed agent
and interface through its help, exposed tools, or current official documentation.
Verify feature flags, authentication, and limits; do not transfer one agent's
requirements to another. Lifecycle states, budgets, and pause/resume vary by runtime.

A goal enforces a contract through verification. It is not a budget command,
a safety boundary, “run forever”, or a replacement for `/plan`.

## When to use it

Use for repeated autonomous work with a **verifiable stop condition**: passing tests, target coverage, eval ≥ X, or a green build. For code work, establish a working build and relevant checks first. No minimum task duration applies.

Fits: migrations, coverage lifts, TDD feature builds, refactors with contract tests, prompt/eval optimization, deploy retry loops, bug-repro-then-fix.

Bad fits: exploratory work, vague "improve this", anything without a "done" definition, prod credentials, destructive shared-infra ops.

## The 4-part contract (every goal needs this)

1. **Objective**, one sentence, one concrete outcome.
2. **Constraints**, what must NOT change (public API, files, libs, conventions).
3. **Validation command**, the exact shell command that proves progress (`pytest -q`, `pnpm test`, etc.).
4. **Stop condition**, verifiable: "Stop when X passes" OR "when further changes need human/product input."

Also specify what to read first, checkpoints, and a short progress log.

## Writing a goal (the core deliverable)

The rest: https://github.com/davidondrej/skills/blob/HEAD/skills/agent-orchestration/goal-loop/SKILL.md