lingtai-update-mainland

lingtai-update-mainland is a skill for Claude Code, Codex from Lingtai-AI/lingtai. It costs 20 tokens per session (961 once invoked), scanned A, original, Apache-2.0.

A release and dependency guide for building or fetching LingTai's text interface and web portal from mainland China. It explains when to use alternate software mirrors and how the installer chooses them.

In plain words
What is it for?
It helps select GitHub or Gitee release sources, configure package mirrors, use the mainland-China installation route, and understand fallback behavior when a mirror cannot be reached.
Why use it?
It addresses unreliable access to public code releases and package registries during installation or updates.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps select GitHub or Gitee release sources, configure package mirrors, use the mainland-China installation route, and understand fallback behavior when a mirror cannot be reached.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lingtai-ai/lingtai/mainland-china
Install

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.

Any agent
npx skills add Lingtai-AI/lingtai --skill mainland-china
Clone the repo
git clone --depth 1 https://github.com/Lingtai-AI/lingtai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for lingtai-update-mainland

README.md
[![agentmods](https://agentmods.dev/badge/skills/lingtai-ai/lingtai/mainland-china/github.svg)](https://agentmods.dev/skills/lingtai-ai/lingtai/mainland-china)
Your own site
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/mainland-china"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/mainland-china/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.

agentmods 80×15 button for lingtai-update-mainland

Your own site · 80×15
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/mainland-china"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/mainland-china.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 961 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00961
Opus 5 $0.00010 $0.00481
Sonnet 5 $0.00004 $0.00192
Haiku 4.5 $0.00002 $0.00096

Measured 5d ago against content hash fc10ab987517, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lingtai-update-mainland scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl` is available and `GOPROXY` is unset; if that probe fails it exports all
tui/internal/preset/skills/lingtai-update/reference/mainland-china/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mainland-China routing

Nested lingtai-update reference. Troubleshooting guidance, not a promise that any mirror is reachable. Before selecting the install flow, install.sh probes https://proxy.golang.org/github.com/golang/go/@latest for three seconds when curl is available and GOPROXY is unset; if that probe fails it exports all three variables below, overwriting existing GOSUMDB or NPM_CONFIG_REGISTRY values:

export GOPROXY="https://goproxy.cn,direct"
export GOSUMDB="sum.golang.google.cn"
export NPM_CONFIG_REGISTRY="https://registry.npmmirror.com"

Release provider and the Python dependency index

install.sh --source auto|github|mirror (or LINGTAI_SOURCE) selects where the release archives, the bundle manifest, and the pinned kernel release come from. auto runs a bounded, fail-open public-IP country lookup and prefers the lingtai.ai download-acceleration mirror for mainland China; any detection or reachability failure falls back to GitHub for the SAME resolved tag/bundle. GitHub remains the sole release/version authority either way — the mirror only re-serves bytes GitHub already published, never its own "latest". (--source gitee is retired: the mirror replaces the earlier Gitee route.) The TUNA dependency-index default is retained from the earlier Gitee path, where an Aliyun-host upgrade failed at third-party dependency resolution through pypi.org. That historical observation is not a live acceptance result for the new lingtai.ai mirror; its production configuration and mainland reachability still require verification.

install.sh now picks exactly one dependency index (python_dependency_index_url):

Situation Index used for third-party dependencies
non-empty LINGTAI_PYPI_INDEX_URL that value, on either provider
final bundle provider is the mirror https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
final bundle provider is GitHub https://pypi.org/simple

"Final" means the provider that actually served the bundle manifest, after any same-tag fallback moved the selection. There is no --extra-index-url: exactly one index is consulted. LingTai itself is never affected — it is always installed from the checksum-verified local artifact by explicit file path and is never requested by package name from any index. Tsinghua TUNA is a cloud-neutral domestic default, not a promise that it is reachable from your host; override it with LINGTAI_PYPI_INDEX_URL when your organization runs its own index.

Read the full file on GitHub · 76 lines

Changes

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.

  1. 5d ago Changed · +4 lines fc10ab987517
  2. 13d ago First seen · 72 lines · 20 tokens per session scan A 90ba55ee6d92

Subscribe to this mod's changes

lingtai-update-mainland is a skill published in the GitHub repository Lingtai-AI/lingtai (677 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 961 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.