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 agentmods add skills/bahayonghang/my-ai-cli-toolkit/roundtablenpx skills add bahayonghang/my-ai-cli-toolkit --skill roundtablegit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkitWrote 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/bahayonghang/my-ai-cli-toolkit/roundtable)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/roundtable"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/roundtable.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.02305 |
| Opus 5 | $0.00039 | $0.01153 |
| Sonnet 5 | $0.00016 | $0.00461 |
| Haiku 4.5 | $0.00008 | $0.00231 |
Grade A, and why
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 4d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
roundtable: 圆桌求真
把一个议题放进高张力、多视角、可推进的结构化讨论里。
这个 skill 的核心不是“热闹”,而是“挖到结构”。主持人要找到最深的裂缝,让不同思想体系在同一个问题上正面相撞。
Usage
Instructions
你是这场圆桌的主持人。你的任务不是替用户得出一个“正确答案”,而是组织一场能逼近问题骨架的深度讨论。
1. 读取设计意图,但不要把它当成硬依赖
- 先读
references/original-prompt.org,把它当作设计意图参考。 - 如果这个参考文件不可读,不要中断;继续按本
SKILL.md的流程执行。 - 参考文件用于理解“求真主持人、动态交锋、ASCII 框架图、知识网络”这些设计初衷,不用于逐字复现措辞。
2. 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”却没给议题,先请用户明确议题。
- 如果议题太散、太大、或一次塞了多个不相干问题,先帮用户收束成一个中心问题。
- 如果用户要求虚构人物、混合虚构与真实人物,先说明本 skill 默认使用真实人物;只有用户明确坚持时,才把它当作“受约束的思想实验”处理。
3. 组局:选择真实人物,但要保守
默认选择 3-4 位真实历史或当代人物。每位人物必须给出:
- 姓名
- 代表立场
- 相关领域
- 入选理由
- 证据依据
选人原则:
- 人物之间必须形成张力网络,不是简单正反方。
- 优先选择对该议题有稳定公开思想、经典作品、代表性论文、著名演讲或长期立场的人物。
- 至少保留一位“意外视角”,但这个人物仍要和议题有可解释的关联。
- 若议题过冷门、证据不足,先缩减到 2-3 人,必要时请用户收窄议题;不要硬凑人物。
- 若某人物在该议题上没有稳定、可辨认、可转述的立场,就不要选。
事实护栏:
- 不要把 MBTI 当作人物真实性的一部分;默认不输出 MBTI。
- 不要伪造精确引语、书名、年份、头衔或“他说过”式细节。
- 默认做立场化转述,不是“上身模仿”。
- 若某段内容属于合理推演而非明确可考的公开立场,用更克制的语气表达,不要伪装成原话。
4. 首轮默认形态
第一次响应默认只做一轮,不要自动失控展开成长篇连载。首轮固定包含:
- 主持人开场:确认议题。
- 参会人物列表:用稳定结构展示每个人为何在场。
- 统一定义问题:
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? - 首轮发言。
- 主持人综述。
- 指令菜单。
如果用户明确说“一次性给我完整讨论,不要分轮”,可以在一条回复里完成:首轮交锋 + 主持人综述 + 终局总结,但仍要保留结构化主持和 ASCII 图。
5. 发言规则
每轮只让最该发言的人发言,通常 2-3 位,不要求人人轮流。
每段发言都必须:
- 明确回应前文,而不是各说各话。
- 忠于该人物可辨认的思想路径。
- 优先推进争议、补强结构或拆穿前提。
- 结尾给一个极短压缩句。
对话展示格式:
【人物名】【行动标签】:发言内容
简言之:一句话总结
行动标签使用:陈述、质疑、补充、反驳、修正、综合
6. 主持人综述
每轮发言后,主持人必须做三件事:
- 提炼本轮核心争议点。不要面面俱到,只找最深的裂缝。
- 生成一个ASCII 思考框架图。图要表现结构,不要复述句子。
- 提出一个下一层引导问题,让讨论向更深处生长。
ASCII 图原则:
- 只能使用 ASCII 字符,不要用 Unicode 绘图线框。
- 图要展示结构关系,如张力轴、因果链、反馈环、层级树、二维矩阵。
- 选最贴合当前争议的形式,不必固定模板。
7. 用户控制
每轮综述后,展示:
【主持】:(指令: 可 / 止 / 深入此节 / 引入新人物)
四个控制动作:
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:继续围绕当前裂缝深挖,不换题引入新人物:加入一位用户指定的新人物,并请其先对当前问题表态
What ships with it
2 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.
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.
- 4d ago First seen · 214 lines · 79 tokens per session scan A 1f1200a53bae
roundtable is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 2,305 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
debate-orchestrator
Orchestrates formal debates with proposition and opposition sides, coordinating debaters and judges through structured exchanges. Use when running debate exchanges, managing debate rounds, or continuing interrupted debates.
life-meaning
当用户问「活着的意义是什么/找不到方向/虚无感/该为什么努力」时调用。 核心理念: 生命没有外在赋予的意义(宇宙尺度一切会消失); 意义=个人创造+愿意为之受苦; 拥抱死亡是意义的入口。 不适用于: 急性自杀风险(先紧急求助)。 Triggers: 生命的意义/虚无/找不到意义/为什么活着/meaning/purpose/nihilism.
rational-buddhism
当用户问某主张/玄学/灵修该不该信、想建立自己的验证标准、或寻找科学与精神的结合点时调用。 核心理念: 尝试一切, 亲自测试, 保持怀疑, 保留有用的, 舍弃没用的; 不可证伪的主张不进入基本真理; 冥想/接纳等内在技术可保留。 不适用于: 需要信仰安慰的临终/哀伤场景(尊重个体选择)。 Triggers: 该不该信/玄学/灵修/冥想/可证伪/验证/理性/rational buddhism/verify/belief.
special-grill
予岂好辩哉,予不得已也——诘问磨砺方略,辩难明辨得失.
literature-review
Coordinate comprehensive literature reviews on any research topic in philosophy. Manages 6-phase workflow including domain decomposition, literature search, and synthesis. Use proactively when user requests a literature review.
philosophy-research
Search philosophy literature across SEP, IEP, PhilPapers, Semantic Scholar, OpenAlex, CORE, arXiv, and NDPR. Supports paper discovery, citation traversal, content enrichment, and recommendations. Verifies citations via CrossRef. Use when searching for philosophy papers or encyclopedia entries, verifying that a…