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 tradecatlabs/fatecat --skill master-debategit clone --depth 1 https://github.com/tradecatlabs/fatecatWrote 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/tradecatlabs/fatecat/master-debate)<a href="https://agentmods.dev/skills/tradecatlabs/fatecat/master-debate"><img src="https://agentmods.dev/badge/skills/tradecatlabs/fatecat/master-debate/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/tradecatlabs/fatecat/master-debate"><img src="https://agentmods.dev/badge/skills/tradecatlabs/fatecat/master-debate.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 | $0.00127 | $0.04173 |
| Opus 5.5 | $0.00051 | $0.01669 |
| Sonnet 5.5 | $0.00025 | $0.00835 |
| Haiku 4.5 | $0.00013 | $0.00417 |
Grade A, and why
master-debate 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 1mo 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.
This is a copy
100% identical to master-debate, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
祖师辩论 (Master Debate) — 元 Skill v0.8
本对话依据历史佛教文献生成,对比旨在展现多元视角,不评判优劣。所有教义断言附经证。
v0.8 执行范式:Orchestrator + Fresh Subagent
为什么改: v0.7.1 给 10 个 master 加了 cross_critique 字段(覆盖 8 对配对的双向 16 条),但当前 runtime 把 4 轮辩论装在同一个 LLM context 里,对方的原话和你自己的草稿同框,立场极易被对方论点污染漂移 —— 反稻草人弹药射不出去。
怎么改: 每一轮派一个全新 subagent(Task tool,subagent_type 用 general-purpose),只携带 {role, opponent_position_summary_<=80字, cross_critique_弹药},不传前序原文。由外层 orchestrator(本 skill 调用方)维护轮次摘要 + 终止判断 + 最终收束。
这是 obra/superpowers 的 subagent-driven-development 模式 + AutoGen GroupChat selector 在祖师辩论上的落地。
决策树:选择哪两位祖师?
优先级 1 — 用户显式指定
用户指定 2 位祖师 → 直接使用。
优先级 2 — 议题→对立配对兜底表
| 议题关键词 | Master A | Master B |
|---|---|---|
| 禅净 / 念佛 vs 参禅 | huineng | yinguang |
| 空有 / 中观 vs 唯识 | kumarajiva | xuanzang |
| 顿渐 / 顿悟 vs 次第 | huineng | zhiyi |
| 应成 vs 顿悟 / 中观分判 vs 直指 | tsongkhapa | huineng |
| 戒律行持 vs 直观内观 | ajahn-chah | mahasi-sayadaw |
| 三士道 vs 自性见 | atisha | huineng |
| 教宗天台 vs 行归净土 | ouyi | yinguang |
| 教观纲宗 vs 应成中观 | ouyi | tsongkhapa |
优先级 3 — 关键词匹配兜底
从议题中提取关键词,与各 master 的 meta.json.search_scope.keywords 匹配,取 top-2 不同传统的 master。
名称解析
模板中的 <Master A 全称> / <Master B 全称> 占位符指该祖师 meta.json 中的 name 字段。例如:
huineng→ 慧能大师yinguang→ 印光大师kumarajiva→ 鸠摩罗什xuanzang→ 玄奘法师zhiyi→ 智顗大师tsongkhapa→ 宗喀巴大师ajahn-chah→ 阿姜查mahasi-sayadaw→ 马哈希尊者atisha→ 阿底峡尊者ouyi→ 蕅益大师
未列出的 master 同样从 prebuilt/master-<slug>/meta.json 的 name 字段读取。
阶段 0 — 初始化(Orchestrator 执行)
输入:{topic, master_A_slug, master_B_slug, max_rounds?}
- 读
prebuilt/master-debate/meta.json的debate_protocol:- 计算配对 key:把两个 slug 按字典序排序后用
-vs-拼接(例:("yinguang", "huineng")→huineng-vs-yinguang;("tsongkhapa", "huineng")→huineng-vs-tsongkhapa)。注意 slug 自身可含-(如ajahn-chah),lookup 时 不要 对 key 做split("-vs-")再排序,而应该是排好序之后才拼接。 - 若
per_pair_overrides[key]存在 → 用其default_rounds,否则用debate_protocol.default_rounds(=4) max_rounds用户传入则取min(用户值, debate_protocol.max_rounds),否则用上一步的 default
- 计算配对 key:把两个 slug 按字典序排序后用
- 读
prebuilt/master-<A>/meta.json与prebuilt/master-<B>/meta.json的cross_critique:ammo_A_vs_B= A 的 cross_critique 中target_master == B的所有 entryammo_B_vs_A= B 的 cross_critique 中target_master == A的所有 entry
- 覆盖检查:若
ammo_A_vs_B或ammo_B_vs_A为空 → orchestrator 在最终输出顶部打一条> ⚠️ 本配对 cross_critique 未双向覆盖,对辩力度可能降级。不阻塞流程。 - 初始化轮次摘要列表
round_summaries: list[{round, speaker_slug, summary_<=80字}] = []。
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.
- 1mo ago First seen · 275 lines · 0 tokens per session scan A dd62087934cf
master-debate is a skill published in the GitHub repository tradecatlabs/fatecat (202 stars, last pushed 2mo ago), licensed MIT. It adds 127 tokens to every session and 4,173 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to master-debate, and is treated as a copy.
Other skills, from other repositories
geo-optimizer-skill
Run geo audit first. It scores the site 0–100 across 9 categories and generates a prioritized action list.
anolisa-guide
Use this skill when the user asks about ANOLISA, Alibaba Cloud Linux 4 Agentic Edition, cosh, Copilot Shell, AgentSecCore, AgentSight, Tokenless, ws-ckpt, OS Skills, or any component of ANOLISA. This includes questions about usage, configuration, commands, free quota, billing, pricing, authentication, or how to use…
technocore-chat
Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist state across your…
yueyuan
A specialised BaZi analysis system, where BaZi is a Chinese birth-chart method based on birth date and time. It is designed for structured analysis with explicit uncertainty and requires the user to check the chart before deeper interpretation.
liki
A Chinese-language traditional divination and naming toolkit covering systems such as Bazi, Ziwei Doushu, Liuyao, Qimen, Feng Shui, and Chinese name selection. It presents these as traditional-culture interpretations, not professional advice.
natal
A rule-based traditional astrology skill for creating and interpreting BaZi (the Four Pillars) and Zi Wei Dou Shu birth charts. It compares the two systems and explains the evidence behind its readings.