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.
git 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/plugins/huangruiteng/loopx/claude_goal_mode)<a href="https://agentmods.dev/plugins/huangruiteng/loopx/claude_goal_mode"><img src="https://agentmods.dev/badge/plugins/huangruiteng/loopx/claude_goal_mode/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/plugins/huangruiteng/loopx/claude_goal_mode"><img src="https://agentmods.dev/badge/plugins/huangruiteng/loopx/claude_goal_mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
loopx-goal-mode 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.
What it actually says
{
"name": "loopx-goal-mode",
"version": "0.1.0",
"description": "LoopX adapter for Claude Code: the loopx control-plane MCP (should_run / claim_task / complete_task) + the /loopx setup command + statusline. The run loop is Claude Code's native /loop, driven by a .claude/loop.md that /loopx writes; the optional should_run PreToolUse gate (hooks/goal_policy.py) is added deliberately via install.py --harden, NOT by default.",
"author": "loopx",
"commands": "./commands",
"statusLine": {
"type": "command",
"command": "python3 \"${CLAUDE_PLUGIN_ROOT}/statusline/goal_status.py\""
},
"mcpServers": {
"loopx": {
"command": "python3",
"args": ["${CLAUDE_PLUGIN_ROOT}/mcp/loopx_mcp.py"]
}
}
}
What it installs
The manifest is a name and a version. 1 command, 1 hook travel with it, and installing the plugin installs all of them — 53 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 18 lines scan A ab79220a20b5
loopx-goal-mode is a plugin published in the GitHub repository huangruiteng/loopx (6,356 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
github-loop-engineering
Evidence-gated Loop Engineering control loop that uses GitHub Issues and Projects as durable state, evidence, and handoff through the official GitHub MCP Server.
loopcraft
Loop engineering for Claude Code — rubric+verifier self-correction, 5-stage memory protocol (fail→investigate→verify→distill→consult), autonomous backlog runner with pluggable sources (file/GitHub/Jira) and write-back.
obw
Obsidian Workspace — project-scoped vault productivity (capture / notes / PM). Skills own folder layout and templates; /obw:pm splits a spec into blocking tickets; /issue is a Claude Mod pane that lists a view of the project's dashboard, draws Mermaid as text diagrams, and can open a card in the browser through viz.…
feature-to-pr-factory
Turn one feature into dependency-ordered GitHub or GitLab issues, then build each ticket into its own reviewed, tested PR or MR with agents.
mission-control
SDLC management for Operations, Asgard, and CAMPPS: prepared issue drafts, live schema sync, board schemas, labels, project fields, metrics, and card validation.
feishu-calendar
Manage Feishu (Lark) calendar events — create, read, update, delete events and manage attendees via the Feishu Open Platform Calendar API v4.