goal-loop SKILL.md skillA

goal-loop from skillmds/skillmd is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add skillmds/skillmd/goal-loop@git:20260919.fecc0d5

Pins git:20260919.fecc0d5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
skillmds/skillmd
Path
plugins/create-agent-skills/skills/goal-loop/SKILL.md
Versions recorded
1
Latest version
git:20260919.fecc0d5, committed Sep 19, 2026
Size
10,376 bytes
Repository stars
250
License
MIT

Draft and explain persistent goal-loop prompts for long-running agent work with clear stop conditions.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agent `/goal` Loop

## What `/goal` is

`/goal` is a slash command that turns an agent 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."

Agents with the `/goal` feature right now: **Codex, Claude Code, and Hermes Agent**.

Key difference from a normal prompt: when a turn ends but the goal isn't met, the agent **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 the user: what the agent 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

- An agent with the `/goal` feature — right now: Codex, Claude Code, or Hermes Agent
- The goals feature enabled in the agent's config
- **Subscription auth** — API-key auth does **not** work. A pro-tier plan is the realistic minimum for long runs.

## When to Use it
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add skillmds/skillmd/goal-loop@sha256:a1ceeff3b819f0ba

The line at the top of this page pins the label git:20260919.fecc0d5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_hr4vxgpf63yrsrdf.svg)](https://markdownregistry.com/a/art_hr4vxgpf63yrsrdf)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 19, 2026.

versioncommittedcommitsizeaudit
git:20260919.fecc0d5 latest2026-09-19 fecc0d5 10,376 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10376 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

skillmds/skillmd · 250 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hr4vxgpf63yrsrdf
GET https://markdownregistry.com/api/v1/resolve?ref=skillmds/skillmd/goal-loop
GET https://markdownregistry.com/api/v1/blob/a1ceeff3b819f0bae95c30e61c84bdba4eb314ddc04831310dbd6346d1a61edd

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from skillmds/skillmd

hello-world SKILL.md skill
skillmds/skillmd · examples/skills/hello-world/SKILL.md · Greet the user warmly and demonstrate the minimal shape of a valid Agent Skill.
git:20260825.90a5e4f · audit A · 250 stars
ads-math SKILL.md skill
skillmds/skillmd · plugins/agents-mcp/skills/ads-math/SKILL.md · Calculate and model paid-media CPA, CPL, CPC, CPM, ROAS, MER, break-even targets, contribution margin, LTV:CAC…
git:20260919.fecc0d5 · audit A · 250 stars
AGENTS.md@plugins/agents-mcp/skills/agent-recall AGENTS.md file
skillmds/skillmd · plugins/agents-mcp/skills/agent-recall/AGENTS.md
git:20260919.fecc0d5 · audit A · 250 stars
agent-recall SKILL.md skill
skillmds/skillmd · plugins/agents-mcp/skills/agent-recall/SKILL.md · Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check…
v3.4.30 · audit A · 250 stars
aihot SKILL.md skill
skillmds/skillmd · plugins/agents-mcp/skills/aihot/SKILL.md · 查询 AI HOT 的中文 AI 资讯、精选、当前热点和日报。当用户问今天或最近的 AI 新闻、AI 圈动态、大模型或产品发布、OpenAI/Anthropic/Google 最近发布、AI 论文、AI 日报、AI HOT…
git:20260919.fecc0d5 · audit A · 250 stars
CLAUDE.md@plugins/agents-mcp/skills/b0 CLAUDE.md file
skillmds/skillmd · plugins/agents-mcp/skills/b0/CLAUDE.md
git:20260919.fecc0d5 · audit A · 250 stars
b0 SKILL.md skill
skillmds/skillmd · plugins/agents-mcp/skills/b0/SKILL.md · Delegate tasks to AI agents via Box0. Use when the user asks to review code, check security, run tests, compare tools…
git:20260919.fecc0d5 · audit A · 250 stars
bioqc-mcp SKILL.md skill
skillmds/skillmd · plugins/agents-mcp/skills/bioqc-mcp/SKILL.md · Automated sequencing quality control and advanced visualization wrapping FastQC, MultiQC, and custom chart generation…
v0.1.0 · audit A · 250 stars
BMW-design-analysis SKILL.md skill
skillmds/skillmd · plugins/agents-mcp/skills/bmw-design-analysis/SKILL.md · BMW's corporate site — distinct from BMW M's motorsport-bombastic variant, this is a measured and settled…
alpha · audit A · 250 stars
civitai-mcp-ultimate SKILL.md skill
skillmds/skillmd · plugins/agents-mcp/skills/civitai-mcp-ultimate/SKILL.md · Ultimate MCP server for Civitai — search models, browse top images with prompts, download LoRAs/Checkpoints, analyze…
git:20260919.fecc0d5 · audit A · 250 stars
claw-orchestrator SKILL.md skill
skillmds/skillmd · plugins/agents-mcp/skills/claw-orchestrator/SKILL.md · Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Cursor, and OpenCode engines. Use when…
git:20260919.fecc0d5 · audit A · 250 stars
cli-anything-hermes SKILL.md skill
skillmds/skillmd · plugins/agents-mcp/skills/cli-anything-hermes/SKILL.md · Use when the user wants Hermes Agent to build, refine, test, or validate a CLI-Anything harness for a GUI application…
git:20260919.fecc0d5 · audit A · 250 stars

Every file in skillmds/skillmd

Other files named goal-loop

goal-loop SKILL.md skill
davidondrej/skills · skills/agent-orchestration/goal-loop/SKILL.md · Draft /goal prompts and explain persistent agent loops. Use for goal or Ralph loops, autonomous run setup, monitoring…
git:20261018.eaed515 · audit A · 4,161 stars
goal-loop SKILL.md skill
aktsmm/agent-skills · goal-loop/SKILL.md · Run an explicit end-to-end goal loop with frozen Scope/criteria, worker delegation, external verification, evaluator…
git:20261004.e1c4ed1 · audit A · 26 stars

Browse by kind, by grade A, or by owner.