Codex Goal Loop

Explain and write effective instructions for OpenAI Codex's `/goal` feature — the persistent self-checking agent loop (plan → act → test → review → iterate). Use when the user mentions Codex `/goal`, "goal loop", "Ralph loop", wants to kick off a long-running autonomous Codex run, asks how to write a goal prompt, or wants a one-paragraph goal instruction drafted.

100 stars 27 forksSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add adriannoes/awesome-agentic-ai --skill codex-goal-loop
Manual install
git clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai.git /tmp/awesome-agentic-ai
mkdir -p ~/.claude/skills
cp -r /tmp/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/agent-orchestration/codex-goal-loop ~/.claude/skills/codex-goal-loop

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Codex `/goal` Loop

## What `/goal` is

`/goal` is a slash command in **Codex v0.128.0+** (April 30, 2026) that turns a Codex prompt into a **persistent agent** looping `plan → act → test → review → iterate` until a stop condition is met, the user pauses, or the token budget runs out. Internally called the "Ralph loop."

Key difference from a normal prompt: when a turn ends but the goal isn't met, Codex **auto-continues** instead of waiting for input.

**Lifecycle states:** `pursuing`, `paused`, `achieved`, `unmet`, `budget-limited`.

When monitoring a running `/goal`, every check should include a one-line update to David: what Codex is doing and whether it is on track. Keep it extremely concise.

**Not:** a budget command, a safety boundary, "run forever", or a replacement for `/plan`. It's a contract enforcer with a verification loop.

## Requirements

- Codex CLI/app/extension v0.128.0+
- `goals = true` in `~/.codex/config.toml` (or `codex features enable goals`)
- **ChatGPT auth** (Plus/Pro/Business/Edu/Enterprise) — API-key auth does **not** work. Pro is the realistic minimum for long runs.

## When to use it

Use only when **all three** are true:
1. Task is >30 min of mechanical work.
2. There's a **verifiable stop condition** (tests pass, coverage hit, eval ≥ X, build green).
3. Repo is agent-ready (working build, decent tests, `AGENTS.md` present).
Read the full skill on GitHub

Details

Skill name
codex-goal-loop
Path
cursor-claude-codex/skills/david-ondrej/agent-orchestration/codex-goal-loop/SKILL.md
License
MIT
Repo updated
2 November 2026

FAQ

What does the Codex Goal Loop skill do?

Explain and write effective instructions for OpenAI Codex's `/goal` feature — the persistent self-checking agent loop (plan → act → test → review → iterate). Use when the user mentions Codex `/goal`, "goal loop", "Ralph loop", wants to kick off a long-running autonomous Codex run, asks how to write a goal prompt, or wants a one-paragraph goal instruction drafted.

How do I install the Codex Goal Loop skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add adriannoes/awesome-agentic-ai --skill codex-goal-loop. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Codex Goal Loop popular?

It lives in adriannoes/awesome-agentic-ai, which has 100 GitHub stars and 27 forks, and is included in 2 curated skill lists.

Related skills

Browserstack

100

adriannoes/awesome-agentic-ai

Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".

Testing & QAIn 2 lists27

Coverage

100

adriannoes/awesome-agentic-ai

Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".

Testing & QAIn 2 lists27

Fix

100

adriannoes/awesome-agentic-ai

Fix failing or flaky Playwright tests. Use when user says "fix test", "flaky test", "test failing", "debug test", "test broken", "test passes sometimes", or "intermittent failure".

Testing & QAIn 2 lists27

Deobfuscating Javascript Malware

100

adriannoes/awesome-agentic-ai

Deobfuscates malicious JavaScript code used in web-based attacks, phishing pages, and dropper scripts by reversing encoding layers, eval chains, string manipulation, and control flow obfuscation to reveal the original malicious logic. Activates for requests involving JavaScript malware analysis, script deobfuscation, web skimmer analysis, or obfuscated dropper investigation.

Software DevelopmentIn 2 lists27

Building Incident Response Playbook

100

adriannoes/awesome-agentic-ai

Designs and documents structured incident response playbooks that define step-by-step procedures for specific incident types aligned with NIST SP 800-61r3 and SANS PICERL frameworks. Covers playbook structure, decision trees, escalation criteria, RACI matrices, and integration with SOAR platforms. Activates for requests involving IR playbook creation, incident response procedure documentation, response runbook development, or SOAR playbook design.

Software DevelopmentIn 2 lists27

Detecting Typosquatting Packages in Npm Pypi

100

adriannoes/awesome-agentic-ai

Detects typosquatting attacks in npm and PyPI package registries by analyzing package name similarity using Levenshtein distance and other string metrics, examining publish date heuristics to identify recently created packages mimicking established ones, and flagging download count anomalies where suspicious packages have disproportionately low usage compared to their legitimate targets. The analyst queries the PyPI JSON API and npm registry API to gather package metadata for automated comparison. Activates for requests involving package typosquatting detection, dependency confusion analysis,

Software DevelopmentIn 2 lists27

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.