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 export-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/export-recipe)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/export-recipe"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/export-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/export-recipe"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/export-recipe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Rogue Agent · line 199 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00048 | $0.04973 |
| Opus 5 | $0.00024 | $0.02486 |
| Sonnet 5 | $0.00010 | $0.00995 |
| Haiku 4.5 | $0.00005 | $0.00497 |
Grade A, and why
recipe-export-flow 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 13d 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exporting a Recipe
Nested lingtai-recipe reference. Read this after the top-level router sends you here.
This is the recipe-export sub-guide of the lingtai-recipe skill. For an overview of all recipe-related flows, read ../../SKILL.md.
Prerequisites: Read ../recipe-format/SKILL.md first — it defines the bundle shape, recipe.json schema, the four behavioral layers (all optional), the library sibling, and how the validator enforces all of it. This sub-guide assumes you understand all of that.
A recipe is the culture of a network, distilled into a portable seed. Your job is to help the human reflect on their network's culture and package the parts worth sharing. An exported recipe is a bundle directory — a git repo the recipient clones and points /setup at.
First: which "recipe" does the human mean?
../../SKILL.md ("Disambiguate scope BEFORE picking a sub-guide") defines the three recipe-shaped artifacts a project can hold at once. Confirm scope with the human before authoring anything, then apply the export-side rule for each:
-
A recipe distilled from the inner network (the agents in
.lingtai/) — the default, and what this sub-guide assumes. You write a NEW.recipe/capturing what makes this network distinctive. -
The outer project's own
.recipe/at the project root (sibling of.lingtai/). If the human says "re-export the recipe," they may mean republish this existing bundle, NOT write a new one. Ask. Republishing is mostly a copy job (copy<project>/.recipe/and the matching<project>/<library_name>/sibling into$HOME/lingtai-agora/recipes/<id>/, then jump to Step 4 to validate). Distilling a fresh recipe is what the rest of this sub-guide covers. -
The applied-recipe snapshot at
.lingtai/.tui-asset/.recipe/— a TUI-managed copy of #2, useful as evidence of what behavior is currently in force. Not a separate artifact to ship: if the human wants what's in there, they almost certainly mean #2.
The most common failure mode in a project that was itself seeded from a recipe (e.g., a methodology recipe applied to produce a domain network): the agent confuses #2 with #1 and ends up republishing the seeding methodology instead of distilling the network's actual culture. If the project has both a .lingtai/ and its own .recipe/ at the root, ASK the human which scope they want before proceeding.
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.
- 13d ago First seen · 300 lines · 48 tokens per session scan A e89e43d0a5b8
recipe-export-flow is a skill published in the GitHub repository Lingtai-AI/lingtai (677 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 4,973 once invoked, about $0.0002 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…