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-recipegit 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-recipe)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/lingtai-recipe"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/lingtai-recipe/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-recipe"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/lingtai-recipe.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 | $0.00130 | $0.01905 |
| Opus 5 | $0.00065 | $0.00953 |
| Sonnet 5 | $0.00026 | $0.00381 |
| Haiku 4.5 | $0.00013 | $0.00191 |
Grade A, and why
lingtai-recipe scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lingtai-recipe: Recipes and How to Publish Them
Bundle root convention: The bundle root is the directory that contains
.recipe/at its top level (alongside the library folder). When pointing the TUI or any tool at a recipe, pass this directory, not.recipe/itself and not a parent of it. For recipes published vialingtai-recipeskill, this is$HOME/lingtai-agora/recipes/<id>/.
A recipe bundle is a required .recipe/ behavioral layer (recipe.json manifest plus optional greet/, comment/, covenant/, procedures/ layer dirs) beside an optional framework-agnostic skill library named by recipe.json#library_name. reference/recipe-format/SKILL.md is authoritative for that structure; this router does not restate it.
Every LingTai project uses a recipe — selected during /setup, inherited from a cloned network, or auto-discovered when a project already has .recipe/ at its root.
This skill is the one place to look for anything recipe-related. Pick the sub-file that matches what you're doing, then read it in full before acting.
Nested reference catalog
lingtai-recipe owns these nested references. They are parent-owned drill-down
files, not standalone top-level skills.
- name: recipe-format-reference
location: reference/recipe-format/SKILL.md
description: |
Authoritative recipe bundle format reference: directory structure,
`recipe.json` schema, optional behavioral layers, locale fallback rules,
library sibling mechanics, validator contract, and custom recipe testing.
- name: recipe-export-flow
location: reference/export-recipe/SKILL.md
description: |
Standalone recipe-export procedure for distilling a live network's culture
into a portable recipe bundle: scope disambiguation, metadata collection,
authoring, validation, sensitivity sweep, git initialization, and handoff.
Routing table
| If you need to... | Read |
|---|---|
Understand or author a recipe bundle: structure, recipe.json, optional layers, locale fallback, library sibling, validation, testing |
reference/recipe-format/SKILL.md |
Export a standalone recipe: distill culture into optional greet/comment/covenant/procedures plus optional skill library; no agents, no mailboxes |
reference/export-recipe/SKILL.md |
What ships with it
5 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.
- 6d ago Changed · -9 lines · -120 tokens per session 30ce788faaa8
- 12d ago First seen · 111 lines · 250 tokens per session scan A 4d1b8abd9775
lingtai-recipe is a skill published in the GitHub repository Lingtai-AI/lingtai (677 stars, last pushed yesterday), licensed Apache-2.0. It adds 130 tokens to every session and 1,905 once invoked, about $0.0006 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…
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…