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 agentmods add skills/huangruiteng/loopx/loopx-pr-reviewnpx skills add huangruiteng/loopx --skill loopx-pr-reviewgit 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-pr-review)<a href="https://agentmods.dev/skills/huangruiteng/loopx/loopx-pr-review"><img src="https://agentmods.dev/badge/skills/huangruiteng/loopx/loopx-pr-review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00079 | $0.02006 |
| Opus 5 | $0.00039 | $0.01003 |
| Sonnet 5 | $0.00016 | $0.00401 |
| Haiku 4.5 | $0.00008 | $0.00201 |
Grade A, and why
loopx-pr-review 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 today.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LoopX PR Review
This skill is a thin host adapter. The built-in pull-request-review
capability owns review depth, evidence requirements, completeness, and verdict
policy through the CLI packet. Do not copy those rules into this skill or
replace them with a host-specific checklist.
Route
Use this skill for /loopx-pr-review, explicit PR reviews, or review queues by
state or time window. Route approval, merge, self-merge, and admin bypass to
loopx-pr-merge after the evidence review is complete.
Run the LoopX CLI before ad hoc GitHub reads:
loopx --format json pr-review --state all
Translate only explicit filters:
--repo owner/repo--since ISO--state open|merged|all--limit N
Words such as today, open, or merged are filters, not permission to
return a table only. Stats-only output requires an explicit opt-out such as
只统计, 只列出, stats only, or 不要 review.
Preserve The Packet
Save the full first JSON packet before printing a compact projection. Keep all
paths named by agent_response_contract.required_packet_fields_to_preserve,
especially:
agent_response_contract.review_execution_contractresult_completenessreview_groupspull_requests[].review_planpull_requests[].review_templatepull_requests[].evidence_commands
Do not pipe the only copy through jq. When an exhaustive request has
result_completeness.complete=false, rerun with its recommended_limit before
reviewing.
Execute One Review Plan
Review review_groups.unmerged first, then review_groups.merged. For every
selected PR:
- Record the packet's exact head and run its
evidence_commands, plus focused repository-native validation when applicable. - Fill
review_plan.result_templatefrom the shared execution contract; preserve missing evidence asunverified. Fordefault_off_isolation, run its paired counterfactual across every shared and automatically loaded surface, including skills, agent instructions, prompt templates, help, schemas, install bundles, and provider guidance. Treat installation, discovery, provider readiness, accepted input, and resolver success as availability rather than activation; a runtime default-off flag cannot compensate for capability behavior already projected through a baseline instruction surface. For scoped activation, verify the intended scope and every required subject before capability-specific guidance or effects. Forauthority_semantics, match names to actor authority. Never inferverifiedfrom metadata or CI. - Apply
completion_gateliterally. If an applicable requirement is missing, do not manufacture a detailed verdict; name the evidence gap. - Render the verified result through
review_template. The five sections are output structure, while the execution contract is the evidence authority. - Re-read the remote head immediately before verdict and publication. Restart the evidence pass if it changed.
What ships with it
1 file 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.
- today Changed · +8 lines 67c7f2d8cf11
- 2d ago Changed f46f561e0768
- 5d ago First seen · 181 lines · 79 tokens per session scan A b6f36f8a6ba0
loopx-pr-review is a skill published in the GitHub repository huangruiteng/loopx (5,609 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 2,006 once invoked, about $0.0004 per session on Opus 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
deep-research
Autonomous multi-step deep research engine implementing an iterative Think → Search → Extract → Synthesize → Stop loop. The LLM drives every decision: what to search, what's relevant, what's missing, and when to stop. Produces a cited, magazine-quality report with inline citations, category- specific formatting, and…
image-studio
Generate, edit and upscale AI images via fal.ai through a three-stage studio workflow — brainstorm a strong prompt with the user, prototype cheaply and iterate on feedback, then produce a finalised image. Use when the user wants image generation or editing through the local fal.ai helper workflow, including requests…
skill-maintainer
Track upstream drift and sync adapted skill libraries.
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…
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.
news-monitoring
Recurring topic/news monitoring with web search, multi-language sources, digest formatting, and automated delivery via Hermes cron jobs. Covers search strategy, source selection, Chinese-language platforms, and digest templates.