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-dev-guidegit 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-dev-guide)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/lingtai-dev-guide"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/lingtai-dev-guide/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-dev-guide"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/lingtai-dev-guide.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 | $0.00080 | $0.02919 |
| Opus 5 | $0.00040 | $0.01460 |
| Sonnet 5 | $0.00016 | $0.00584 |
| Haiku 4.5 | $0.00008 | $0.00292 |
Grade A, and why
lingtai-dev-guide 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LingTai Developer Guide
The cross-repository developer router for LingTai. The root stays short on
purpose; detailed procedures live under reference/<topic>/.
Repository-local developer guidance takes precedence
Before using this guide, look for developer guidance maintained by the current repository and read it first. When it exists, follow it for repository-specific rules; it takes precedence over this global guide. Use this guide afterward — or when the local guide routes here — to select the deeper cross-repository topic you need, then read that nested reference before touching code. Do not substitute generic procedures here for local guidance, or restate local rules from memory.
Non-negotiable rules
- Progressive disclosure: router → nested reference → anatomy skill → code + tests. Never jump from memory straight to edits.
- Code is truth: reference files route and summarize; cited source files,
tests, and
ANATOMY.mdfiles are authoritative. - Anatomy travels with code: if you move/rename/split/delete code cited by an
ANATOMY.md, update the anatomy in the same commit, following the ANATOMY frontmatter contract below. - Explicit human authorization gates: do not open/merge PRs, push commits, file issues, close/delete resources, or change config unless the human gave an imperative authorization for that side effect.
- Human-facing deliverables prefer HTML: substantial plans, audits, release notes, and PR-readiness reports should be standalone HTML unless waived.
- Release/install docs rule: LingTai runtime is normally managed by the
TUI-created project venv; do not present bare
pip install/upgrade lingtaias the standard user path. Manual pip/venv commands are for developer, diagnostic, or verification contexts only. - Patch-to-self ownership rule: a merged PR or rebuilt checkout is not
automatically live in the agent. The update/build owner must identify the
actual runtime interpreter, imported source/package, HEAD/version, and intended
selectors, then hand off the cutover target evidence. Kernel
system-manual→reference/refresh-precheck/SKILL.mdalone owns the refresh transaction and targeted receipt. Loadreference/runtime-self-check/SKILL.mdonly for the relevant provenance assertion or a suspected mismatch; an ordinary same-runtime reload does not invoke its deep diagnostic library. - Skill-size/progressive-disclosure rule: when writing or updating skills,
treat read/context limits as a reason to keep the router lean and link onward,
not as a reason to paste large content into
SKILL.md. Put dense material in related/nested reference files and link toskills-manualfor current authoring mechanics and limit-aware structure. - Launch-session / PYTHONPATH hygiene rule: never launch the TUI or an agent
from a shell session that exports
PYTHONPATH. A leftoverPYTHONPATHpointing at another project's scratch/worktree/temp reposrcshadows the venv's ownlingtaiimport, and because the refresh watcher copiesos.environverbatim, the pollution survives refresh — a plainrefreshre-inherits it. Debug sessions thatexport PYTHONPATH=...for one experiment silently infect every agent they launch. Seereference/gotchas/SKILL.md("PYTHONPATH pollution") andreference/runtime-self-check/SKILL.md§1 for the probe and §8 for the clean-relaunch recipe.
What ships with it
12 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.
- reference/architecture/SKILL.md 7.2 KB
- reference/cache-hit-rate/scripts/cache_hit_rate.py 12 KB runs code
- reference/cache-hit-rate/SKILL.md 9.8 KB
- reference/contributing/SKILL.md 16 KB
- reference/debug-troubleshoot/SKILL.md 16 KB
- reference/gotchas/SKILL.md 11 KB
- reference/pr-review-deliverables/SKILL.md 7.3 KB
- reference/repo-watch/SKILL.md 4.4 KB
- reference/runtime-self-check/SKILL.md 18 KB
- reference/security-audit/SKILL.md 13 KB
- reference/setup/SKILL.md 8.1 KB
- reference/skill-stewardship/SKILL.md 8.3 KB
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 · +5 lines 3efbd84021d8
- 4d ago Changed · -12 tokens per session 8e5a81e9e496
- 11d ago First seen · 217 lines · 92 tokens per session scan A e4601cd1df40
lingtai-dev-guide is a skill published in the GitHub repository Lingtai-AI/lingtai (673 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 2,919 once invoked, about $0.0004 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…