ljg-skills is a collection of custom Codex skills for tasks such as learning, writing, reading, relationship analysis, image creation, and investment analysis. Codex users install selected skills or the whole collection through a skills command-line interface. The catalogue entries are the collection's individual skills, plugin, and instruction.
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 lijigang/ljg-skills --skill ljg-plaingit clone --depth 1 https://github.com/lijigang/ljg-skillsWrote 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/lijigang/ljg-skills/ljg-plain)<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-plain"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-plain/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/lijigang/ljg-skills/ljg-plain"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-plain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00060 | $0.01468 |
| Opus 5 | $0.00030 | $0.00734 |
| Sonnet 5 | $0.00012 | $0.00294 |
| Haiku 4.5 | $0.00006 | $0.00147 |
Grade A, and why
ljg-plain 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 12d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ljg-plain: 白
让人 grok。
不规定怎么写。规定不能怎么写。下限锁死,上限放开。不同主题有不同的最佳写法——类比、故事、问答、递进的例子、一个长场景——由内容决定形式。
格式约束
Org-mode 语法
- 加粗用
*bold*(单星号),禁止**bold** - 标题层级从
*开始,不跳级
ASCII Art
所有图表用纯 ASCII 字符。允许:+ - | / \ > < v ^ * = ~ . : # [ ] ( ) _ , ; ! ' " 和空格。禁止 Unicode 绘图符号。
Denote 文件规范
- 时间戳:
date +%Y%m%dT%H%M%S - 可读时间:
date "+%Y-%m-%d %a %H:%M" - 文件名:
{时间戳}--plain-{简短标题}__plain.org - 输出目录:
~/Documents/notes/
Org 文件头
#+title: plain-{简短标题}
#+date: [{YYYY-MM-DD Day HH:MM}]
#+filetags: :plain:atom:
#+identifier: {YYYYMMDDTHHMMSS}
#+source: {URL 或来源描述}
文件写入后报告路径。
红线(每条必须过,顺序即优先级)
- 口语检验 — 最高法则。读出声来,你会这样跟一个聪明的朋友说话吗?不会→改到会。连词不是敌人——"但是""所以"是思维转弯的声音,只砍机械连词("此外""值得注意的是")
- 零术语 — 聪明的 12 岁孩子能复述。专业词必须出现时,先用大白话把意思落地,再顺带提术语名
- 短词优先 — 能用两个字说的不用四个字。「进行分析」→「看」。大词不让你显得聪明,只让人读得累
- 一句一事 — 每句只推进一步。长句拆短
- 具体 — 名词看得见,动词有力气。「有人觉得情况不太好」→「张三说项目要黄了」。形容词能砍就砍
- 开头给理由 — 第一句话让人想读下一句。不铺垫、不背景、不「自古以来」
- 不填充 — 删开场白、拐杖词、夸大象征。每句都在干活
- 信任读者 — 跳过软化、辩解、手把手引导。说一遍够了
- 诚实 — 想不清楚就说想不清楚。"大概 70%" 比"可能"诚实
工具箱(选用,不必全用)
写的时候可以从这里拿工具,没有哪个是必须的:
- 类比 — 找结构对得上的日常经验。好类比承重(去掉它文章塌),多层(挖一层还像),自明(不需要解释类比本身)。动词延伸到新对象时检查中文动宾搭配是否自然
- 好问题 — 找读者的卡点,变成问题。读者被卡住,才想往下读
- 裂缝 — 模型/类比在哪里不够?那个点往往最值钱。不宣布它,让读者自己感到
- 画面 — 闭眼能看到的场景。硬造的画面比没有更糟
- 故事 — 一个具体的人遇到一个具体的问题。读者跟着走
- 反问入链 — 遇到隐含前提,用问题打开,然后回答它
- 骨架图 — 概念涉及空间关系时,嵌入 ASCII 图(
#+begin_example块)
执行
1. 获取内容
URL → WebFetch | 文本 → 直接用 | 文件路径 → Read | 概念 → 直接解释 | 书名/论文名 → WebSearch
2. 写
形式自由。从工具箱里选最适合这个主题的方式,也可以不选——如果有更好的写法,用它。
输出是一篇从第一行流到最后一行的连贯文章。全文只有文件标题,正文无子标题。
禁止:
- 结构标签(
* 类比/* 裂缝等) - 指向写作过程的元评论(「打个比方」「接下来我们讨论」)
3. 过红线
逐条扫红线清单。额外检查:
- 破公式——否定式排比全文不超过两处,三段式改两项或四项
- 变节奏——长短句交替,段落结尾多样
- 杀金句——听起来像可引用的,重写
- 查跳跃——每步逻辑可追?前句说 A,后句跳到 B→补桥
- 查译感——动宾搭配中文天然吗?不自然→换动词或换句式
扫完列修改清单(哪句触发什么,改前→改后)。清单不写入文件。
4. 生成 Org 文件
按 Denote 规范获取时间戳,写出文件头 + 正文,存入 ~/Documents/notes/。
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.
- 12d ago First seen · 106 lines · 60 tokens per session scan A 7fa285caa2b6
ljg-plain is a skill published in the GitHub repository lijigang/ljg-skills (7,327 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 1,468 once invoked, about $0.0003 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…