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 skill-stewardshipgit 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/skill-stewardship)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/skill-stewardship"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/skill-stewardship/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/skill-stewardship"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/skill-stewardship.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 Rogue Agent · line 5 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00099 | $0.01907 |
| Opus 5 | $0.00049 | $0.00954 |
| Sonnet 5 | $0.00020 | $0.00381 |
| Haiku 4.5 | $0.00010 | $0.00191 |
Grade A, and why
dev-guide-skill-stewardship 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 11d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Stewardship
Nested lingtai-dev-guide reference. Read this after the top-level router sends you here when deciding whether to write a skill, distilling experience into one, or cleaning a skill up so it can ship in a PR.
This consolidates the skill-distillation meta-method (归一), skill audit/triage,
the experience-to-skill side of session-journal handoff, the skill-benchmark
checklist, and shared-library grooming. It governs LingTai's skill hygiene; for
generic authoring mechanics (frontmatter spec, trigger syntax, file layout)
cross-link to skills-manual rather than duplicating it here.
Core principle
A skill turns a repeated experience into something triggered, executable, verifiable, and maintainable. Write one when the technique would otherwise be re-derived ad hoc across sessions or agents — and only after it is de-privatized and lightly benchmarked. Skills shipping in this repo's preset tree must be parameterized: no private paths, no human-specific details, no secrets.
1. When to write a skill
Write one when the technique was not intuitively obvious and you would reference it again; when multiple agents/sessions keep re-implementing the same workflow with divergent quality (convergent discovery is the strongest signal); or when the pattern is broadly reusable rather than a one-off.
Do not write a skill for one-off solutions or single-incident narratives; for
standard practices already documented elsewhere (link instead); for
project-specific conventions (those belong in CLAUDE.md/repo docs); or for
mechanical constraints a test/regex could enforce (automate, don't document).
If it is real but not yet skill-worthy, leave it as a session-journal entry or a shared-library candidate (§5) until the pattern repeats.
2. Routing vs nested-reference pattern
LingTai utility skills use progressive disclosure: a short router SKILL.md at
the root plus focused nested references under reference/<topic>/SKILL.md.
Read/context limits are a design signal, not a global hard-cap to keep open
forever. Do not encode an old tool threshold as a blanket character limit, and do
not paste dense material into the root just because a reader might need it later.
The root carries only the progressive-disclosure link; the related/reference file
carries the detail and loads on demand. For current mechanics (frontmatter,
layout, validator, limit-aware structure), load skills-manual.
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.
- 11d ago First seen · 159 lines · 99 tokens per session scan A dccef192c7ad
dev-guide-skill-stewardship is a skill published in the GitHub repository Lingtai-AI/lingtai (673 stars, last pushed yesterday), licensed Apache-2.0. It adds 99 tokens to every session and 1,907 once invoked, about $0.0005 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…