# Swe Marathon Five Arm

> Migrate historical SWE-Marathon agent configurations to the shared Codex runtime.

- Skill: `loopx-project/swe-marathon-five-arm` (Agent Skill)
- Install (CLI): `npx skillmds@latest add loopx-project/swe-marathon-five-arm`
- Raw SKILL.md: https://api.skillmd.com/api/skills/loopx-project/swe-marathon-five-arm/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: loopx-project (https://skillmd.com/u/loopx-project)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/loopx-project/swe-marathon-five-arm

---


# SWE-Marathon shared execution

Read `../../runtime/RUNTIME.md` and `../../../runtime/RUNTIME.md` before preparing
a new study. Use the shared Harbor adapter and its explicit execution_mode and
iteration_context, preserving native tasks, verifier policy and scoring.

The historical five-arm WEN framework is retired. Do not run its assisted
unblock or sandbox-replacement wrappers, reinterpret withdrawn results, or
invent an independent validator from git status. Existing study data and
withdrawal notices remain tied to their original source revision.

Validate the chosen native environment with a bounded task before a full run.
Model jobs, verifier access and publication require the caller's authorization;
loading this migration guide grants none of those actions.