LoopX is a provider-neutral control plane that gives long-running AI-agent work persistent state, decisions, governance, recovery, and handoffs across different agent harnesses. It is for managing and reviewing durable work performed by Codex, Claude Code, Cursor, dsh, or custom agent systems.
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.
npx skills add huangruiteng/loopx --skill swe-marathon-five-armgit clone --depth 1 https://github.com/huangruiteng/loopxWrote 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.
[](https://agentmods.dev/skills/huangruiteng/loopx/swe-marathon-five-arm)<a href="https://agentmods.dev/skills/huangruiteng/loopx/swe-marathon-five-arm"><img src="https://agentmods.dev/badge/skills/huangruiteng/loopx/swe-marathon-five-arm/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.
<a href="https://agentmods.dev/skills/huangruiteng/loopx/swe-marathon-five-arm"><img src="https://agentmods.dev/badge/skills/huangruiteng/loopx/swe-marathon-five-arm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 94 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 96 Potential security issue detected. Manual review is recommended.Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Rogue Agent · line 40 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 40 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.00172 |
| Opus 5.5 | $0.00009 | $0.00069 |
| Sonnet 5.5 | $0.00004 | $0.00034 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
swe-marathon-five-arm 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 28d ago.
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.
What it actually says
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.
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.
- 28d ago Changed · -286 lines · -70 tokens per session 3afce763a8ca
- 1mo ago First seen · 306 lines · 92 tokens per session scan A 515460981fcd
swe-marathon-five-arm is a skill published in the GitHub repository huangruiteng/loopx (6,233 stars, last pushed 5d ago), licensed Apache-2.0. It adds 22 tokens to every session and 172 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
deep-research
Use when the user asks for "deep research", a "research report on", a "comprehensive analysis of", to "look into X in depth", to "write a report on X", or any question needing multi-source synthesis beyond a single search — an autonomous multi-step deep research engine implementing an iterative Think → Search →…
image-studio
Use when the user wants image generation or editing through the local fal.ai three-stage studio workflow — brainstorm a strong prompt, prototype cheaply and iterate on feedback, then produce a finalised image. Covers "generate an image", "make an image/picture/illustration/graphic of…", "create an AI image"…
website-scraping
Generic playbook for extracting structured data from any website — hotel prices, flight fares, e-commerce listings, real estate, jobs, competitor product catalogues, anything where the goal is to turn one or more URLs into clean records on disk. Use this skill whenever the user mentions scraping, harvesting…
skill-maintainer
Use when tracking upstream drift and syncing adapted skill libraries.
library-rag
Semantic search over a personal library using Nemotron-3-Embed-1B embeddings + sqlite-vec. Index books, documents, any text corpus; query by meaning. Includes EPUB→Markdown conversion and MCP server for auto-available search tools.
notebooklm-mode
Source-grounded research pipeline inspired by NotebookLM. Collect verbatim source extracts into a temporary workspace, then answer questions and create deliverables grounded in those sources. Two grounding modes: strict (vault-only) and augmented (vault + labeled [background] knowledge). Trigger when the user asks to…