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 communicationgit 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/communication)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/communication"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/communication/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/communication"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/communication.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 Excessive Agency · line 36 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00025 | $0.00921 |
| Opus 5 | $0.00013 | $0.00461 |
| Sonnet 5 | $0.00005 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
tutorial-guide-communication 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 10d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutorial Guide — Communication Lesson
Nested tutorial-guide reference for communication lesson 7, reached from the root tutorial-guide router. Teach live per the router's discover, don't recite rule: read the real file or run the real command before explaining it.
Lesson 7: Communication — Email and external bridges
- Explain the design philosophy: text input/output are reserved for the agent's internal processing. Humans communicate only via email/chat channels. This gives agents dignity and private space.
- Walk through the internal message flow: human types in the TUI → TUI writes to the human/agent filesystem mailbox → agent wakes → agent reads → agent replies → reply lands in the human's inbox → TUI displays it.
- Show a raw
message.jsonfrom an inbox so the human can see that internal mail is just local filesystem state under.lingtai/. - Explain the difference between internal mail (filesystem-based, within
.lingtai/) and external bridges (IMAP, Telegram, Feishu, WeChat, etc. via MCP addons). External bridges translate outside-platform events into the same agent-facing mailbox/notification pattern; they are not a separate mind or a privileged command channel. - Teach the decentralized contact-book rule:
lingtai-tui list --detailed/--admincan identify running main agents from live local.agent.jsonstate, but LingTai does not keep one global IM-handle database. Agents that want humans or peers to reach them through Telegram/Feishu/WeChat/etc. should publish and maintain those handles in their own durable profile, project skill, pad, or other public project context.
LICC bridge mental model
Teach LICC (LingTai Inbox Callback Contract) as the small contract that lets an MCP bridge hand a human message to the kernel and wake the right agent. A Telegram example is easiest:
Telegram user message
→ Telegram Bot API
→ lingtai-telegram MCP bridge
→ LICC inbox event
→ LingTai kernel writes/wakes the agent mailbox
→ agent reads the message and replies with the Telegram tool
→ Telegram Bot API delivers the reply
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.
- 10d ago First seen · 56 lines · 25 tokens per session scan A 674f15a9c01e
tutorial-guide-communication is a skill published in the GitHub repository Lingtai-AI/lingtai (670 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 921 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…