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 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/tui)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/tui"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/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/tui"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/tui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 66 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00000 | $0.02919 |
| Opus 5 | $0.00000 | $0.01460 |
| Sonnet 5 | $0.00000 | $0.00584 |
| Haiku 4.5 | $0.00000 | $0.00292 |
Grade A, and why
tui 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 4d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL.md — Preset model lists & provider integration
Bookkeeping notes for keeping providerModels, route-specific model lookup,
modelHasVision, and friends in preset_editor.go aligned with each
provider's real-world catalog. Read this before editing those maps so you
don't bork an agent network with a typo or a retired model.
What this file is for
providerModels (preset_editor.go:108) is the canonical native/default-route
catalog. Every model picker, display, and free-text decision calls
modelOptions(provider, base_url): exact route overrides keep a proven native
catalog separate from a protected gateway catalog, while an uncurated route
remains free text. The lookup is the source of truth for editor behavior.
Drift here causes one of two failures:
- Silent staleness: the picker doesn't show a model the user knows exists, so they have to free-text edit it. Annoying, recoverable.
- Loud breakage: the picker offers a model the provider has retired or doesn't actually serve on our chosen endpoint. Agents pick it from the list, get 4xx/5xx, escalate to STUCK/AED. The user blames Lingtai, not OpenAI.
The second failure mode is what this file exists to prevent.
Shared service-tier editor behavior
serviceTierOptions (preset_editor.go) is the one normal | fast vocabulary
used by the preset editor for every provider, including Codex Pool, API-key,
CLI-backed, and Custom built-ins. The row is always visible and cyclable. A
missing or normal value displays as normal and omits
manifest.llm.service_tier on commit; fast persists as the string "fast".
The TUI deliberately performs no provider support check or filtering here — a
lower layer may ignore an unsupported tier. This is independent of the
provider model catalogs and does not change model, reasoning, credential, or
endpoint behavior. Unknown legacy values display as normal; non-Codex values
retain the existing preservation behavior unless the user cycles the row.
Authoritative sources per provider
What ships with it
60 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.
- addon.go 5.4 KB
- agent_rail_collapse_test.go 45 KB
- agent_rail.go 7.6 KB
- agent_selector.go 9.4 KB
- agents_direct_conversation_boundary_test.go 13 KB
- agora_removed_test.go 1.6 KB
- ANATOMY.md 95 KB
- app_cpr_test.go 1.8 KB
- app_cursor_test.go 9.6 KB
- app_recipe_test.go 5.9 KB
- app_test.go 6.2 KB
- app_visit_test.go 14 KB
- app.go 83 KB
- apriori_summary_render_test.go 10 KB
- auto_refresh_test.go 6.8 KB
- auto_refresh.go 1.4 KB
- claude_auth_test.go 2.5 KB
- claude_auth.go 2.8 KB
- clear_test.go 8.2 KB
- clear.go 5.9 KB
- clipboard_image_test.go 2.4 KB
- clipboard_image.go 1.9 KB
- codex_auth_active_test.go 9.6 KB
- codex_auth_agents_test.go 11 KB
- codex_auth_store_test.go 11 KB
- codex_auth_store.go 20 KB
- codex_cli_import_test.go 10 KB
- codex_model_probe.go 6.9 KB
- codex_pool_store_test.go 25 KB
- codex_pool_store.go 18 KB
- copy_mode_test.go 4.8 KB
- ctrl_o_anchor_test.go 3.5 KB
- ctrl_r_refresh_test.go 6.1 KB
- daemons_test.go 27 KB
- daemons.go 34 KB
- detect_test.go 2.6 KB
- detect.go 4.1 KB
- direct_chat_paging_contract_test.go 15 KB
- direct_chat_performance_contract_test.go 11 KB
- direct_chat.go 20 KB
- direct_cleanup_contract_test.go 1010 B
- direct_ordering_main_boundary_test.go 14 KB
- direct_refresh_update_io_red_test.go 7.9 KB
- direct_selector_affinity_red_test.go 36 KB
- direct_sparse_history_allocations_red_test.go 6.7 KB
- direct_visibility_unread_red_test.go 22 KB
- doctor_intrinsic_test.go 2.3 KB
- doctor_intrinsic.go 5.0 KB
- doctor_report_test.go 6.6 KB
- doctor_startup_test.go 14 KB
- doctor_view_test.go 4.1 KB
- doctor.go 62 KB
- e2e_opencode_go_test.go 14 KB
- firstrun_legacy_init_fields_test.go 3.0 KB
- firstrun_test.go 40 KB
- firstrun.go 170 KB
- global_select_mode_test.go 4.3 KB
- goal_test.go 4.6 KB
- goal.go 3.9 KB
- help_test.go 6.3 KB
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.
- 4d ago Changed · +39 lines 1fcb7a8c04de
- 9d ago First seen · 100 lines · 0 tokens per session scan A a8567bc33de9
tui is a skill published in the GitHub repository Lingtai-AI/lingtai (677 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,919 tokens. 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 2026-09-03.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…