Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Lingtai-AI/lingtainpx agentmods add skills/lingtai-ai/lingtai/installWrote 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/install)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/install"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/install/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/install"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/install.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 14 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Tool Misuse · line 14 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
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 | $0.00022 | $0.00634 |
| Opus 5 | $0.00011 | $0.00317 |
| Sonnet 5 | $0.00004 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade C, and why
lingtai-update-install scanned grade C with 2 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 2d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://lingtai.ai/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://lingtai.ai/install.sh | bash What it actually says
Install and build
Nested lingtai-update reference. The supported public first-install path is:
curl -fsSL https://lingtai.ai/install.sh | bash
install.sh resolves the latest release from GitHub; the source option selects
the download route, not version authority
(--source auto|github|mirror, default auto, or LINGTAI_SOURCE;
--source gitee is retired), prefers a matching lingtai-<tag>-<os>-<arch>.tar.gz
asset, and falls back to building the release source when no asset is
available. It installs both binaries into a selected bin directory and
prepares the TUI-managed runtime; that runtime is not a second TUI update path.
On the verified-bundle path the Python lingtai runtime is installed from the
bundle's pinned kernel artifact by explicit local file path after a SHA256
check — never by requesting the package name lingtai from an index. Only that
artifact's third-party dependencies use a package index, and exactly one:
a non-empty LINGTAI_PYPI_INDEX_URL always wins, otherwise the provider that
actually served the bundle manifest decides (the lingtai.ai mirror →
https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple, GitHub →
https://pypi.org/simple). There is no --extra-index-url. See
reference/mainland-china/SKILL.md for the reachability reasoning; Windows
(install.ps1) and --latest are outside this behavior.
For a deliberate source build, the current repository layout is:
cd tui && make build
cd ../portal && make build
The portal build first needs its checked-in web dependencies and frontend build
(cd portal/web && npm ci && npm run build); portal/embed.go then embeds the
result into lingtai-portal. Go and Node are build prerequisites, not runtime
dependencies of the portal binary.
The installer accepts --version <tag>, --ref <ref>, --bin-dir <dir> or
--prefix <dir>; its --update --prefix <prefix> --version <tag> --non-interactive form is the source updater contract. Prefer the public
lingtai.ai URL for new installs. Homebrew remains a supported migration path;
bare pip install/upgrade lingtai is kernel development/diagnosis guidance, not
normal TUI update guidance.
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.
- 2d ago Changed · +1 lines aa9b82e0ffbf
- 9d ago First seen · 53 lines · 22 tokens per session scan C 24de10a754bf
lingtai-update-install is a skill published in the GitHub repository Lingtai-AI/lingtai (700 stars, last pushed yesterday), licensed Apache-2.0. It adds 22 tokens to every session and 634 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…