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 Lingtai-AI/lingtai --skill mainland-chinagit clone --depth 1 https://github.com/Lingtai-AI/lingtaiWrote 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/lingtai-ai/lingtai/mainland-china)<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.
<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>- 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 | $0.00020 | $0.00961 |
| Opus 5 | $0.00010 | $0.00481 |
| Sonnet 5 | $0.00004 | $0.00192 |
| Haiku 4.5 | $0.00002 | $0.00096 |
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 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.
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.
- 5d ago Changed · +4 lines fc10ab987517
- 13d ago First seen · 72 lines · 20 tokens per session scan A 90ba55ee6d92
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.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.