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-materialgit 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-material)<a href="https://agentmods.dev/skills/huangruiteng/loopx/loopx-material"><img src="https://agentmods.dev/badge/skills/huangruiteng/loopx/loopx-material/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-material"><img src="https://agentmods.dev/badge/skills/huangruiteng/loopx/loopx-material.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 | $0.02009 |
| Opus 5.5 | $0.00030 | $0.00804 |
| Sonnet 5.5 | $0.00015 | $0.00402 |
| Haiku 4.5 | $0.00007 | $0.00201 |
Grade A, and why
loopx-material 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LoopX Material
Use this skill for the lifecycle and authority of a project's durable material store. Source discovery, domain-specific scoring, and note writing may be provided by project skills; this skill owns the generic lossless lifecycle.
LoopX ships the canonical source for this skill, but does not install it into the user's global skill directory. Install a managed copy only in a connected project that explicitly enables Material Lifecycle:
loopx project-skill install \
--project . \
--skill loopx-material \
--surface codex \
--execute
Use --surface claude-code or --surface opencode for those hosts; repeat the
flag to install multiple host-native copies in one transaction. Managed copies
live under .agents/skills/, .claude/skills/, or .opencode/skills/ and are
upgraded or removed through the same CLI. Project-local discovery does not
itself activate material-store writes; the selected goal still needs explicit
Material Lifecycle authority.
Activation Gate
Before changing a material store:
- Resolve the current project,
goal_id, registered agent, and active todo throughloopx start-goal --guided,loopx status, orloopx diagnose. - Run
loopx project-skill status --project . --skill loopx-materialand confirm the required host surfaces are current. - Confirm the selected todo explicitly targets
material_lifecycle, or that the goal authority declares an active Material Lifecycle profile and its source store. A catalog entry or project-local skill is not activation. - Confirm the goal boundary covers the exact private adapter and authority paths. Public LoopX contracts never grant access to private source content.
- Run
loopx material-lifecycle architecture --format jsonand preserve its default-off, owner-gated, provider-neutral boundaries.
If the project-local skill is missing, preview an explicit project install; do not fall back to a global copy. If activation or authority is missing, stop before source mutation. Create a bounded setup todo or owner gate; do not invent a store or treat chat history as authority.
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 · 240 lines · 74 tokens per session scan A 234f7ed6b5f2
loopx-material 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 2,009 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
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
rem-page-org
What an organisation's page in the notebook is made of — the fixed sections, when a company earns a page at all instead of staying a field on a person's, and the rules that keep it from becoming a second copy of everyone who works there. Composed into every stage that writes one.
rem-project-sessions
Write or update one project page from the owner's messages and a bounded packet of local project evidence.