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/xr843/master-skill/master-debatenpx skills add xr843/Master-skill --skill master-debategit clone --depth 1 https://github.com/xr843/Master-skillWrote 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/xr843/master-skill/master-debate)<a href="https://agentmods.dev/skills/xr843/master-skill/master-debate"><img src="https://agentmods.dev/badge/skills/xr843/master-skill/master-debate.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 5.1 | $0.00127 | $0.04174 |
| Opus 5 | $0.00063 | $0.02087 |
| Sonnet 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- master-debate — 100% identical, 2 lines differ
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.
- 6d ago First seen · 275 lines · 127 tokens per session scan A e4840c2700cc
master-debate is a skill published in the GitHub repository xr843/Master-skill (382 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 4,174 once invoked, about $0.0006 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
sutra-commentary
Use when the user asks how classical commentators explained a passage of Buddhist scripture — 经注对读, 历代注疏怎么说, 各家怎么注, 这句经谁注过, 注疏对比, 疏解, 古注, commentary on a sutra passage. Triggers include 「这句经历代怎么讲」「各家注疏怎么说」「注疏对读」「谁注过这一句」「注家有什么分歧」「金刚经这一段的注解」. Invoke whenever the question is about what commentators said about a specific…
understand-explain
Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.
baoyu-comic
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
offensive-exploit-dev-course
Full exploit development course roadmap and syllabus: weekly topics, recommended reading, lab setup, and learning path from vulnerability classes through advanced exploitation. Use to structure exploit dev training or onboard new researchers.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
learning-and-development
Builds capability — skills gaps, career frameworks, training that transfers to the job, and internal mobility. Use this to design a career ladder, close a capability gap, decide whether to build or hire a skill, structure onboarding into a role, or work out why training keeps failing to change anything.