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 gotchasgit 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/gotchas)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/gotchas"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/gotchas/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/gotchas"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/gotchas.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 | $0.00055 | $0.02724 |
| Opus 5 | $0.00028 | $0.01362 |
| Sonnet 5 | $0.00011 | $0.00545 |
| Haiku 4.5 | $0.00006 | $0.00272 |
Grade A, and why
dev-guide-gotchas 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 yesterday.
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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gotchas and Known Pitfalls
Nested lingtai-dev-guide reference. Read this after the top-level router sends you here. Collective wisdom from production incidents — each entry has caused at least one regression.
Bubble Tea v2: paste delivery
Bubble Tea v2 splits keys (tea.KeyPressMsg) from clipboard pastes (tea.PasteMsg). Any Update dispatcher handling case tea.KeyPressMsg: must also forward tea.PasteMsg to whichever text widget is focused, or paste silently drops.
For embedded sub-models (e.g. PresetEditorModel inside FirstRunModel), the host's outer default: branch must forward paste msgs into the sub-model. If the host's dispatcher enumerates focused widgets per-step but misses the step hosting an embedded model, paste dies before reaching it — and a fall-through inside the sub-model's own Update is useless because the msg never arrives.
Symptom: typing into an input works, pasting does nothing.
Fix: trace top-down (tea.Program → host's outer switch → sub-model's outer switch → widget) and ensure every layer handles or forwards tea.PasteMsg.
textarea vs textinput
textinput is single-line and drops characters on multi-byte / clipboard pastes; textarea handles paste cleanly. For any paste-friendly field (API keys, base URLs, anything pasted from a browser), use textarea even when the content is conceptually one line:
ta := textarea.New()
ta.CharLimit = 512
ta.SetWidth(50)
ta.SetHeight(1)
ta.ShowLineNumbers = false
ta.Prompt = ""
ta.KeyMap.InsertNewline.SetKeys() // single-line: no newline insertion
ta.SetStyles(themedTextareaStyles())
themedTextareaStyles() is in the tui package — always apply it. A bare textarea.New() ships dark default cursor/focus colors that render as a black smear against the warm LingTai theme.
Dev-mode rebuild gotcha (retired)
Project migrations are retired: production TUI/Portal no longer read, write,
advance, or gate on .lingtai/meta.json, so a stale dev binary against a newer
project no longer trips a data version N is newer than this binary supports
gate. No meta.json version preflight is needed before replacing a local dev
binary, and you never "fix" a project by editing meta.json downward — the file
is inert. Rebuilding a fresh binary after ordinary code changes is still the
right way to make main behaviour live; the only live migration surface left is
the TUI's per-machine ~/.lingtai-tui/ registry (tui/internal/globalmigrate/),
which runs at TUI startup and needs no paired portal bump.
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.
- yesterday Changed 5bda038dc342
- 11d ago First seen · 184 lines · 55 tokens per session scan A 0de5cc3d4c64
dev-guide-gotchas is a skill published in the GitHub repository Lingtai-AI/lingtai (673 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 2,724 once invoked, about $0.0003 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…