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 loopx-doc-registrygit 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/loopx-doc-registry)<a href="https://agentmods.dev/skills/huangruiteng/loopx/loopx-doc-registry"><img src="https://agentmods.dev/badge/skills/huangruiteng/loopx/loopx-doc-registry/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/loopx-doc-registry"><img src="https://agentmods.dev/badge/skills/huangruiteng/loopx/loopx-doc-registry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.00645 |
| Opus 5.5 | $0.00030 | $0.00258 |
| Sonnet 5.5 | $0.00015 | $0.00129 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
loopx-doc-registry 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LoopX Doc Registry
Use this skill for durable project materials. The goal is to make future agents find the material from the project authority surface, not only from chat or personal memory.
Default Route
- Resolve the target project and stable
goal_idfrom the current repo or the user's named project. Prefer.loopx/registry.jsonand.codex/goals/<goal-id>/ACTIVE_GOAL_STATE.md. - If the material belongs to that project, register it in that project's own
authority surface. Do not register it into
loopx-metajust because the current worker discovered it. - If the project has a tracked
docs/meta/DOC_REGISTRY.yamlor equivalent, update that first. If it does not, use.loopx/registry.jsonas the project-local doc registry throughauthority_registry.topic_authorityandauthority_registry.project_materials. - Run
loopx register-authority-sourcewith a redacted source contract. Raw URLs, doc ids, local private paths, comments, and source bodies must not be stored in public files. - Refresh status or state so review packets, read-only maps, dashboards, and heartbeat workers can find the material.
Memory extensions are allowed only as secondary personal reminders. They are not a substitute for project-local authority registration when the project is connected to LoopX.
Command Shape
From the target project:
loopx --registry .loopx/registry.json register-authority-source \
--goal-id <goal-id> \
--source-id <stable-source-id> \
--source-ref "<raw-url-or-private-path-to-hash>" \
--source-kind <doc|lark_doc|wiki|paper|owner_packet|migration_report> \
--role <public-safe-role> \
--freshness <current|historical|unknown> \
--owner-status <public-safe-owner-status> \
--gate-status <readable|needs_access|owner_review_pending> \
--boundary private_redacted \
--revision "<public-safe-revision-label>" \
--conflict-rule "<public-safe-conflict-rule>" \
--topic <topic-key>
Use --dry-run first when the source classification or target project is not
obvious.
What ships with it
2 files 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.
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.
- 1mo ago First seen · 67 lines · 74 tokens per session scan A c5ad255cab5c
loopx-doc-registry is a skill published in the GitHub repository huangruiteng/loopx (6,356 stars, last pushed yesterday), licensed Apache-2.0. It adds 74 tokens to every session and 645 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
cua-volume
Use Cua Volume, the one volume every Space and agent of this user shares. Inside a Space it is mounted as a folder (/volume on Linux, /Cua Volume on macOS), so any program reads and writes it directly. Use it for anything that must outlive this Space - your memory and outputs in your agent home, shared reference in…
obsidian
Obsidian vault: search/read/write notes, backlinks, Bases, Canvas.
docx
Create, read, edit, review, redline, comment on, merge, audit, render, and verify .docx Word documents, including layout-sensitive and OOXML-level work.
excel-author
Create and edit Excel (.xlsx) workbooks with openpyxl. Supports formulas, charts, formatting, and data analysis.
ppt-author
Create and edit PowerPoint (.pptx) presentations programmatically. Requires python-pptx.
ocr-document
Extract text from PDFs, images, and scanned documents. Uses pymupdf (local) or optional cloud OCR APIs.