ralph-loop

ralph-loop is a skill for Claude Code, Codex from foryourhealth111-pixel/Vibe-Skills. It costs 29 tokens per session (501 once invoked), scanned A, original, Apache-2.0.

A command-line runner for Ralph loops, which repeatedly gives an agent a task while keeping progress in a local state file. It supports a local compatibility mode and an optional external loop engine.

In plain words
What is it for?
Use it to start, continue, inspect, restart, or limit iterative agent work with prompts, iteration counts, and completion conditions.
Why use it?
It helps break a larger coding task into repeated iterations and preserve the loop’s status between runs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to start, continue, inspect, restart, or limit iterative agent work with prompts, iteration counts, and completion conditions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/foryourhealth111-pixel/vibe-skills/ralph-loop
About the project

Vibe-Skills is a collection and routing system that helps AI agents discover, select, and coordinate specialized skills for completing tasks. It is intended for agents that need to organize workflows across many installed capabilities. The catalogue entries are skills and an agent belonging to this system.

foryourhealth111-pixel/Vibe-Skills · 3,252 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add foryourhealth111-pixel/Vibe-Skills --skill ralph-loop
Clone the repo
git clone --depth 1 https://github.com/foryourhealth111-pixel/Vibe-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ralph-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/foryourhealth111-pixel/vibe-skills/ralph-loop/github.svg)](https://agentmods.dev/skills/foryourhealth111-pixel/vibe-skills/ralph-loop)
Your own site
<a href="https://agentmods.dev/skills/foryourhealth111-pixel/vibe-skills/ralph-loop"><img src="https://agentmods.dev/badge/skills/foryourhealth111-pixel/vibe-skills/ralph-loop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ralph-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/foryourhealth111-pixel/vibe-skills/ralph-loop"><img src="https://agentmods.dev/badge/skills/foryourhealth111-pixel/vibe-skills/ralph-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 501 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00501
Opus 5 $0.00015 $0.00251
Sonnet 5 $0.00006 $0.00100
Haiku 4.5 $0.00003 $0.00050

Measured 9d ago against content hash 60579d603e3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ralph-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ralph-loop.ps1), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

bundled/skills/ralph-loop/SKILL.md · 56 lines

What it actually says

ralph-loop

This is a Codex-oriented ralph-loop command with two execution engines.

Engine model

  • Keeps the same command name: ralph-loop.
  • Keeps the same default state file format: .claude/ralph-loop.local.md.
  • Default compat engine keeps local-state semantics and manual --next.
  • Optional open engine delegates to external open-ralph-wiggum CLI for auto-iteration.

Script

  • Script path: scripts/ralph-loop.ps1

Usage

$codexHome = if ($env:CODEX_HOME) { $env:CODEX_HOME } else { Join-Path $HOME '.codex' }
$script = Join-Path $codexHome 'skills/ralph-loop/scripts/ralph-loop.ps1'

# Start a local compat loop
powershell -ExecutionPolicy Bypass -File $script Build a todo API --max-iterations 20 --completion-promise DONE

# Move to the next iteration manually
powershell -ExecutionPolicy Bypass -File $script --next

# Show current loop state
powershell -ExecutionPolicy Bypass -File $script --status

# Force restart with a new prompt
powershell -ExecutionPolicy Bypass -File $script New prompt --max-iterations 10 --force

# Use open-ralph-wiggum backend (auto loop, defaults to --agent codex and --no-commit)
powershell -ExecutionPolicy Bypass -File $script --engine open Build a todo API --max-iterations 20 --completion-promise DONE

Vibe compatibility

  • Safe in /vibe routed sessions as a direct execution tool.
  • Does not force multi-agent orchestration.
  • Keeps command names stable for unified memory and invocation.
  • open engine remains mutually exclusive with active XL team orchestration.

Notes

  • Compat mode: if max_iterations is reached, the local state file is removed automatically.
  • Compat mode: completion promises are tracked in local state.
  • Open mode: --next, --force, --state-file, --stop are not available (managed by external ralph CLI semantics).
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 56 lines · 29 tokens per session scan A 60579d603e3b

Subscribe to this mod's changes

ralph-loop is a skill published in the GitHub repository foryourhealth111-pixel/Vibe-Skills (3,252 stars, last pushed 12d ago), licensed Apache-2.0. It adds 29 tokens to every session and 501 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.