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 update-tuigit 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/update-tui)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/update-tui"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/update-tui/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/update-tui"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/update-tui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 Rogue Agent · line 3 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 35 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 58 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 67 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 71 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.01068 |
| Opus 5 | $0.00010 | $0.00534 |
| Sonnet 5 | $0.00004 | $0.00214 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
lingtai-update-command 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 11d 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.
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.
/update-tui
Nested lingtai-update reference. /update-tui compares the running TUI with
the latest GitHub release, detects the install method, and requires explicit
confirmation before changing the TUI binary; the selected distribution may also
refresh the co-installed portal binary. It never updates the Python kernel,
presets, or utility library, and never auto-restarts the current TUI — relaunch
after a successful update.
- Homebrew: migrates to LingTai's native installer instead of running brew.
Runs the version-pinned raw release script
https://raw.githubusercontent.com/Lingtai-AI/lingtai/<tag>/install.shwith--update --prefix <native-prefix> --version <tag> --non-interactive, accepting and updating existing managed runtime/receipt state in place while preserving the exact target tag rather than using ordinary first-install mode. then verifies the newinstall.jsonsource metadata, the binary version at the newbin_dir, and the Python runtime. On any migration failure the old Homebrew formula/keg remains exactly as usable as before the attempt — the migration step itself never runsbrew. Before reporting success, the migration also resolveslingtai-tuion PATH and checks it against the freshly installed binary — on a standard Apple-Silicon Homebrew host,/opt/homebrew/binis earlier on PATH than install.sh's default native bin dir, so a fresh native install alone does not make the shell start running it. When PATH still resolves to Homebrew, the migration reports "native installed, migration not complete" instead of "Migrated!", and every update entry point (startup prompt,self-update,doctor) re-detects and re-reports that same truthful state on every subsequent run — it does not re-run the installer and does not claim success until PATH actually resolves the native binary. Only once that is confirmed doesdetectTUIInstallMethodreport the install as source/user-local going forward, so subsequent updates use the source path below instead of brew. - Source/user-local: runs the versioned
install.sh --update --prefix ... --version <tag> --non-interactivepath and verifies the result.
If a legacy ~/.lingtai-tui/runtime exists before a native receipt, the
installer's documented recovery path is a TUI-only install with
--skip-python (or --skip-venv): it preserves that runtime unchanged and
publishes the native binaries/receipt beside it. Use the standalone fix.sh
with an explicitly named free runtime child only after reviewing its
read-only diagnosis; it must create a parallel runtime and never overwrite the
legacy one.
- Unknown/other or non-comparable/dev versions: reports guidance and does not guess a package manager.
Homebrew removal is a separate, interactive-only decision. Once a native
install is verified — either right after a fresh migration's PATH takeover
succeeds, or on a later launch that redetects an existing verified-but-shadowed
install — the interactive startup prompt (not /update-tui's Bubble Tea
view, not self-update, not doctor) asks a concrete second question:
"Remove the old Homebrew installation now? [y/N]" (default No). Only an
explicit "y" runs the single injected uninstall
(brew uninstall lingtai-ai/lingtai/lingtai-tui, exactly this formula), then
re-resolves lingtai-tui on ordinary PATH and requires it to match the
verified native binary before reporting cleanup complete — the currently
running Homebrew process is never treated as proof. A declined prompt, a
failed uninstall, or PATH still not resolving to the native binary afterward
all leave removal reported as pending, and the same question is asked again
on the next interactive launch. self-update, doctor, and /update-tui
never ask this question and never run brew uninstall — they only report
both the native and Homebrew paths/versions and the exact manual command.
lingtai-tui self-update is the shell command for the same manual update
surface when the interactive TUI is unavailable. lingtai-tui doctor is a
broader repair/report path that can also run the detected TUI backend; use this
skill only for its TUI/portal side and defer Python-runtime decisions to the
kernel system-manual runtime/kernel update manual.
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.
- 11d ago First seen · 76 lines · 20 tokens per session scan A a5fcca8ded52
lingtai-update-command is a skill published in the GitHub repository Lingtai-AI/lingtai (673 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 1,068 once invoked, about $0.0001 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
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…