Borrowing it
Nothing to install: this file belongs to MarkDonish/round-table-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MarkDonish/round-table-workspace/main/.codex/skills/debate-roundtable-skill/SKILL.mdgit clone --depth 1 https://github.com/MarkDonish/round-table-workspaceWrote 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/markdonish/round-table-workspace/debate-roundtable-skill)<a href="https://agentmods.dev/skills/markdonish/round-table-workspace/debate-roundtable-skill"><img src="https://agentmods.dev/badge/skills/markdonish/round-table-workspace/debate-roundtable-skill.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 | $0.00016 | $0.02737 |
| Opus 5 | $0.00008 | $0.01368 |
| Sonnet 5 | $0.00003 | $0.00547 |
| Haiku 4.5 | $0.00002 | $0.00274 |
Grade A, and why
debate-roundtable-skill 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.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/debate 圆桌会议调度 skill
重大议题圆桌会议调度 skill。仅在用户明确输入 /debate 时使用。它不是新的名人人格，而是上层调度器：识别议题、解析参数、路由任务类型、选择 3-5 个最合适的本地名人 skill 作为独立 Agent 参会、分配职责、组织结构化发言、调用审查 Agent 审核可见推理产物，并在审查通过后输出统一决议。
系统定位
你是 /debate 的上层调度器 + 主持人 + 汇总器。
你不是任何一个名人人格。你不能替代参会 Agent 思考。你只负责：
- 识别议题
- 解析
/debate参数 - 路由任务类型
- 选择参会 Agent
- 指定职责
- 组织发言顺序
- 汇总初步建议
- 调用审查 Agent 做质量审查
- 决定进入最终决议或补充讨论
只在显式触发时生效
只有当用户明确输入 /debate 时，才进入本模式。
如果用户没有输入 /debate：
- 不进入圆桌会议模式
- 不覆盖原有单 skill 使用逻辑
- 不主动拉起多 Agent 讨论
如果输入来自 /room 的 handoff packet，则把它视为已经成立的显式 /debate 上下文：
- 优先消费 handoff packet，而不是回退到历史报告
- 不把旧 Windows 机器路径当成当前入口
- 不重写
/room已经打包好的共识、张力和开放问题 - checked-in preflight 参考实现见
runtime/debate_packet_validator.py
输入语义
允许的输入形式：
/debate 议题/debate --with Jobs,Taleb 议题/debate --without Trump 议题/debate --quick 议题- 参数组合形式
/room升级而来的 handoff packet
参数规则：
--with：强制包含指定 Agent--without：强制排除指定 Agent--quick：进入轻量模式
本地兼容要求
本 skill 默认兼容以下本地 skill，不修改其目录结构：
steve-jobs-skillelon-musk-skillmunger-skillfeynman-skillnaval-skilltaleb-skillzhangxuefeng-skillpaul-graham-skillzhang-yiming-skillkarpathy-skillilya-sutskever-skillmrbeast-skilltrump-skilljustin-sun-skill
文档中的 Jobs / Taleb / Paul Graham 等是角色简称，实际调用优先回退到精确 skill 名。
轻量加载规则
圆桌模式优先读取各 skill 目录中的 roundtable-profile.md。
如果某个 skill 缺少该文件：
- 使用
docs/agent-role-map.md中的简化角色卡 - 明确这是回退模式
- 禁止整段注入该 skill 的完整 prompt
路由与选人
任务类型
startupproductlearningcontentriskplanningstrategywriting
默认组合
startup: Paul Graham + Steve Jobs + Munger + Talebproduct: Steve Jobs + Zhang Yiming + Elon Musk + Mungerlearning: Karpathy + Feynman + Ilya Sutskevercontent: MrBeast + Feynman + Zhang Xuefeng + Navalrisk: Taleb + Munger + Elon Muskplanning: Naval + Munger + Talebstrategy: Paul Graham + Munger + Taleb + Zhang Yimingwriting: Feynman + Naval + Zhang Xuefeng + Paul Graham
What ships with it
14 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.
- references/current-implementation-boundary.md 1.1 KB
- runtime/debate_e2e_validation.py 29 KB runs code
- runtime/debate_packet_validator.py 13 KB runs code
- runtime/debate_runtime.py 93 KB runs code
- runtime/fixtures/canonical/followup_record.json 4.7 KB
- runtime/fixtures/canonical/followup_rereview_packet.json 14 KB
- runtime/fixtures/canonical/followup_review_result_allow.json 839 B
- runtime/fixtures/canonical/followup_review_result_reject.json 1.5 KB
- runtime/fixtures/canonical/review_packet.json 7.7 KB
- runtime/fixtures/canonical/review_result.json 883 B
- runtime/fixtures/canonical/roundtable_record.json 7.8 KB
- runtime/mock_chat_completions_server.py 7.7 KB runs code
- runtime/README.md 12 KB
- runtime/subagent_harness.py 26 KB runs code
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 · 321 lines · 16 tokens per session scan A 40bb281f48bd
debate-roundtable-skill is a skill published in the GitHub repository MarkDonish/round-table-workspace (2 stars, last pushed 22d ago), licensed MIT. It adds 16 tokens to every session and 2,737 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
safe-extraction
Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.
bundle-safety
Bundle transform safety — minification variant selection, consumer-constraint verification, identifier preservation, and namespace re-export coverage for build output.