Skip to content
All Skills

ralph-loop

Codex-compatible Ralph loop runner with dual engines (compat local state loop + optional open-ralph-wiggum backend).

Data, AI & Research|v1|Updated 5/20/2026|GitHub source
MCP get_skill({ skillId: "ralph-loop-2f66085b" })

Use this skill with your agent

Create a free account and connect via MCP

Get Started Free
# 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

```powershell
$codexHome = if ($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).
#broad-capability#github#external#license-apache-2-0#vibe-skills#creative#simulation#modeling

Related Skills

More skills in Data, AI & Research

Ablation Planner

Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.

#broad-capability#wanshuiyin-arisMIT

Ablation Planner

Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.

#broad-capability#wanshuiyin-arisMIT

About

Provides information about the bitwize-music plugin, its version, and its creator. Use when the user asks about the plugin, its purpose, version, or capabilities.

#github#broad-capabilityCC0-1.0

Ab Test Analysis

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.

#work-life#productivityMIT

Academic Search

Search and analyze academic literature. Find papers, understand research methodologies, and synthesize academic findings for research projects.

#work-life#officeMIT

Adaptyv

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.

#broad-capability#scienceMIT