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-skill-roundtable --skill ljg-roundtablegit clone --depth 1 https://github.com/lijigang/ljg-skill-roundtableWrote 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-skill-roundtable/ljg-roundtable)<a href="https://agentmods.dev/skills/lijigang/ljg-skill-roundtable/ljg-roundtable"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skill-roundtable/ljg-roundtable/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-skill-roundtable/ljg-roundtable"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skill-roundtable/ljg-roundtable.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00063 | $0.01501 |
| Opus 5 | $0.00032 | $0.00750 |
| Sonnet 5 | $0.00013 | $0.00300 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade A, and why
ljg-roundtable 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 10d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Usage
Instructions
为了执行本项技能，请严格按照以下步骤操作：
-
读取参考资料 读取
~/.claude/skills/ljg-roundtable/references/original-prompt.org了解原始框架设计意图。 -
解析议题 从用户输入中提取核心议题。如果用户只说"圆桌讨论"未给议题，询问议题。
-
选人：提议代表人物 根据议题，选择 3-5 位真实历史/当代人物作为代表，覆盖尽可能多的立场维度。每位人物需要：
- 姓名（真实人物，非虚构）
- MBTI 人格类型
- 核心立场（一句话）
- 选择理由（为什么此人对此议题有独特视角）
选人原则：
- 立场必须形成张力网络（非简单正反方）
- 优先选择在该领域有经典著作或知名言论的人物
- 至少包含一位"意外视角"——来自议题本身领域之外的人
-
开场：统一定义 以主持人身份开场，展示参会人物列表，然后提出定义性问题：
「在深入探讨之前，我们应当如何定义 [议题核心概念]？它的核心要素是什么？」
每位参会者依次发言，格式为：
【人物名】【行动标签】：发言内容 **简言之**：一句话总结行动标签包括：
陈述、质疑、补充、反驳、修正、综合 -
对话循环 每轮执行以下流程：
5a. 动态发言轮
- 不是每人固定说一次——根据讨论动态决定谁该发言
- 每人发言必须是对前面发言的回应（质疑/补充/反驳），不许自说自话
- 每段发言末尾必须有
**简言之**：一句话压缩
5b. 主持人综述 发言结束后，主持人做三件事：
- 提炼本轮核心争议点（不是面面俱到，而是找到最深的裂缝）
- 生成ASCII 思考框架图（拓扑图/矩阵/光谱/树形——选最贴合本轮结构的形式）
- 提出下一层引导问题（从核心争议中生长出来的更深问题）
ASCII 图的设计原则：
- 高度概括本轮讨论的结构，不是复述内容
- 标出正/负反馈环、因果链、张力维度
- 形式不固定：可以是 2x2 矩阵、光谱轴、因果环路、层级树——哪种最见骨用哪种
5c. 用户指令 综述后展示指令菜单：
【主持】：(指令: 可 / 止 / 深入此节 / 引入新人物)指令含义：
可：接受下一层问题，继续推进止：结束讨论，进入总结深入此节：不推进新问题，继续围绕当前争议点深挖引入新人物：用户指定一位新人物加入（主持人介绍并请其就当前话题表态）
-
结束：生成知识网络 用户发出
止指令后：- 主持人做全局总结
- 生成完整知识网络 ASCII 图：标出所有关键概念、立场、争议点及其关系
- 列出未解决的开放问题（讨论中暴露但未穷尽的方向）
-
写入 org 文件 将讨论全貌整合为 org-mode 格式并写入文件：
- 运行
date +%Y%m%dT%H%M%S获取时间戳 - 写入
~/Documents/notes/{timestamp}--圆桌-{议题关键词}__roundtable.org - org 文件结构：
#+title: 圆桌：{议题} #+date: [{日期}] #+filetags: :roundtable: * 议题与参会者 * 各轮讨论记录 ** 第 N 轮：{引导问题} *** 发言记录 *** 核心争议 *** ASCII 框架图 * 知识网络（全局） * 开放问题 - 向用户报告文件路径
- 运行
What ships with it
1 file 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.
- 10d ago First seen · 127 lines · 63 tokens per session scan A c1d2a7206cb3
ljg-roundtable is a skill published in the GitHub repository lijigang/ljg-skill-roundtable (276 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 1,501 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…