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 coveragegit 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/coverage)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/coverage"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/coverage/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/coverage"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/coverage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00030 | $0.01422 |
| Opus 5.5 | $0.00012 | $0.00569 |
| Sonnet 5.5 | $0.00006 | $0.00284 |
| Haiku 4.5 | $0.00003 | $0.00142 |
Grade A, and why
bot-guide-coverage 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coverage matrix and source ownership
Nested lingtai-bot-guide reference. “All related information” means one easy entry to every current owner, not copied full manuals or one universal helper. Names below resolve through the installed skills catalog. Read the selected owner's current node; version differences and missing nodes are explicit gaps.
| Creation topic | Authoritative current owner + exact pointer | Bot-guide entry |
|---|---|---|
| Directory, new-vs-existing, interactive/headless creation | lingtai-tui-help plus headless anatomy (RunSpawn) and process anatomy (CreateProject) |
initiation |
| Kernel-only create/run/schema, no TUI | Installed kernel CLI help; system-manual → reference/substrate-manual/SKILL.md §11; kernel README |
initiation |
| Recipe author/import/export/library and snapshot distinction | lingtai-recipe → reference/recipe-format/SKILL.md, reference/export-recipe/SKILL.md; preset anatomy (recipe_apply.go, recipes.go, state.go) |
initiation |
| Provider/model/endpoint/auth choice | lingtai-preset-skill → reference/{codex,claude,openai,anthropic}/SKILL.md; provider child owns login/secret fields |
initiation |
| Template/saved preset storage and allowed policy | lingtai-preset-skill → reference/operations/saved-presets/SKILL.md; system-manual → substrate §11 |
initiation / headless bot |
| Endpoint/capability evidence and save gate | lingtai-preset-skill → reference/operations/endpoint-capabilities/SKILL.md, reference/operations/availability-save-gate/SKILL.md |
initiation |
| Admin/orchestrator/member ownership | TUI anatomy and system-manual → substrate §11; current creation/schema owner, not manual .agent.json writes |
initiation |
| Installation, bootstrap and service supervision | lingtai-update → reference/install/SKILL.md; system-manual → reference/runtime-update-checks/SKILL.md; shell-manual scheduled-work node |
initiation |
| Telegram helper and actual scope | headless bot, which owns the bundled Telegram helper; preset anatomy embeds/materializes it | headless bot |
| Telegram, Feishu, WeChat, WhatsApp, IMAP, Cloud Mail | mcp-manual → reference/curated-addons.md plus exact upstream README routes and mounted channel manual |
channels |
| Other third-party channels/services | mcp-manual → reference/third-party-and-legacy.md and that server's registry homepage/README |
channels |
| Secret privacy, account login, allowlists, expiry/re-auth | Selected curated/provider README and mounted manual; curated-addons.md WeChat checklist and Telegram readiness/security; no schema copied here |
channels / headless bot |
| Catalog ≠ registered ≠ active; LICC vs tool calls | mcp-manual router and reference/curated-addons.md; lingtai-kernel-anatomy → reference/mcp-protocol.md |
channels / operations |
| End-to-end allowed-user inbound/reply and human receipt | Selected channel manual/readiness owner; bot-level acceptance sequencing in operations | operations |
| Refresh, preset activation, interruption safety | system-manual → reference/refresh-precheck/SKILL.md; lingtai-preset-skill → reference/operations/activation-session-refresh/SKILL.md |
operations |
| Binary/kernel versions, source/venv drift, MCP child provenance | lingtai-update → detection/diagnosis/update-tui nodes; system-manual → runtime-update-checks; mcp-manual curated child-runtime/venv-swap sections |
operations |
| Recovery, partial creation, duplicate start, migration | headless/process anatomies; system-manual → substrate/refresh-precheck; lingtai-preset-skill → reference/operations/troubleshooting-migration/SKILL.md |
operations |
| Independent avatar vs daemon, parent/child reporting | avatar-manual, daemon-manual; system-manual → substrate §1 |
avatars |
| Detached async/scheduled hazards | shell-manual root async-supervision rules and its reference/scheduled-work/SKILL.md |
operations |
| Durable behavior, identity, memory and reusable skills | psyche-manual, context-manual, knowledge-manual, skills-manual; lingtai-dev-guide → reference/skill-stewardship/SKILL.md |
operations |
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 · 58 lines · 30 tokens per session scan A 93d0c38a8fb3
bot-guide-coverage is a skill published in the GitHub repository Lingtai-AI/lingtai (507 stars, last pushed 6d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,422 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…