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 lingtai-tui-helpgit 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/lingtai-tui-help)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/lingtai-tui-help"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/lingtai-tui-help/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/lingtai-tui-help"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/lingtai-tui-help.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 | $0.00088 | $0.01525 |
| Opus 5 | $0.00044 | $0.00763 |
| Sonnet 5 | $0.00018 | $0.00305 |
| Haiku 4.5 | $0.00009 | $0.00153 |
Grade A, and why
lingtai-tui-help 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 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.
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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LingTai TUI help — the discoverable umbrella
Mental model — read this first
lingtai-tui and lingtai-portal are control and presentation surfaces. The
running agent is a separate LingTai kernel process with its own heartbeat,
listeners, lifecycle, and durable working directory.
- Closing the TUI or its terminal quits the interface; it does not stop a running agent. Reopening the TUI observes the current state and does not silently revive an intentionally stopped agent.
- Agent lifecycle changes are explicit. Use
/sleep,/suspend,/cpr, or/refreshaccording to the intended transition; uselingtai-tui list --detailedor/projectsto inspect current state. launchdis not the default remedy for ordinary persistence after TUI exit. The agent already runs independently; adding another supervisor can create duplicate-process races. Use a separate scheduler/service contract only for a separately authorized advanced workflow.- For source-backed proof, load
lingtai-tui-anatomy, start at the repository rootANATOMY.md, and descend totui/ANATOMY.mdorportal/ANATOMY.md. Kernel-side process, heartbeat, listener, and lifecycle internals belong tolingtai-kernel-anatomy; cross-repo references stay narrative.
Sanitized regression question: “关闭 TUI/终端后 agent 会不会停止？” No. UI exit
is not an agent lifecycle command; the agent continues until an explicit
lifecycle action or an external process failure stops it. Do not install a
launchd job merely to keep an ordinary agent alive after closing the TUI.
Feature route catalog
This YAML is the machine-readable map. Each route names the first owner to
load; next is optional deeper evidence.
- feature: runtime-lifecycle-source
route: lingtai-tui-anatomy
next: lingtai-kernel-anatomy
- feature: slash-commands-keyboard-interaction
route: assets/slash-commands.en.md
localized_routes: [assets/slash-commands.zh.md, assets/slash-commands.wen.md]
- feature: presets-providers-capabilities
route: lingtai-preset-skill
- feature: portal-visualization-replay
route: lingtai-portal-guide
- feature: tutorial-orientation
route: tutorial-guide
- feature: install-update-build
route: lingtai-update
- feature: contributor-setup-source-troubleshooting
route: lingtai-dev-guide
- feature: runtime-health-doctor
route: lingtai-doctor
- feature: projects-and-running-agent-inventory
route: assets/slash-commands.en.md
localized_routes: [assets/slash-commands.zh.md, assets/slash-commands.wen.md]
next: lingtai-tui-anatomy
- feature: addons-and-external-channels
route: mcp-manual
What ships with it
3 files 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.
- 5d ago Changed · -1 lines · -18 tokens per session 399516e48a57
- 12d ago First seen · 118 lines · 106 tokens per session scan A ecba33f24176
lingtai-tui-help is a skill published in the GitHub repository Lingtai-AI/lingtai (677 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 1,525 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
help
Get help with Conductor - commands, usage examples, and best practices.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.