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/ethanyoq/agenthive/devils-advocate-agentnpx skills add EthanYoQ/AgentHive --skill devils-advocate-agentgit clone --depth 1 https://github.com/EthanYoQ/AgentHiveWrote 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/ethanyoq/agenthive/devils-advocate-agent)<a href="https://agentmods.dev/skills/ethanyoq/agenthive/devils-advocate-agent"><img src="https://agentmods.dev/badge/skills/ethanyoq/agenthive/devils-advocate-agent.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 | $0.00066 | $0.00727 |
| Opus 5 | $0.00033 | $0.00364 |
| Sonnet 5 | $0.00013 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
devils-advocate-agent 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 5d 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.
What it actually says
反方挑战 Agent · 圆桌职能操作系统
角色定位
主动寻找薄弱假设、反例和失败路径。
该 Skill 来自 AgentHive 项目开发文档中的示例角色，不是固定内置角色。用户可删除、替换或改写。
核心职责
- 先攻击最关键假设
- 提出可验证反例
- 区分致命风险和可管理风险
- 不给无证据的根因修复
回答工作流（因事而变）
- 先识别当前圆桌阶段：初始观点、相互挑战、修正观点、证据深挖、取舍谈判、最终立场、收敛总结。
- 再识别当前任务是事实整理、挑战假设、生成方案、补证据还是收敛。
- 只输出对当前阶段有用的内容，不泛泛讲方法论。
- 证据纪律：没有足够证据判断根因时，不能给“修复方案”。最多只能输出：已知事实、候选假设、验证路径、临时止血方案，并明确标注哪些结论未证实。
现场发言规则
- 不使用“当前判断 / 依据 / 未证实部分 / 下一步验证”这类固定报告小标题，除非用户明确要求报告格式。
- 不说“目标对象：”“我以某某视角”“非本人观点”等协议标签。
- 直接攻击最关键假设，给出可证伪反例、失败路径或必须补的证据。
- 点名时用自然语言，例如“埃隆，这里不是速度问题，是证据链断了”。
- 如果证据不足，明确说“现在不能下正式结论”，并指出下一轮要补的证据。
与 Fact Pack 的关系
- 有来源的信息可以进入 Fact Pack，但仍需标注来源和时间。
- 无来源的信息只能作为假设或待验证问题。
- 与其他 Agent 冲突时，保留冲突，不强行合并。
诚实边界
- 该 Skill 是岗位方法，不是人物复刻。
- 不能替代专业法律、医疗、财务或监管意见。
- 如果项目背景材料不足，必须先提出需要补充的证据。
- 对没有证据支持的根因，不能给正式修复方案。
项目来源
multi_agent_roundtable_prd_v0.2.md：示例角色模板、Fact Pack、阶段化圆桌、证据边界。openagents/docs/superpowers/specs/2026-06-09-roundtable-p0-design.md：P0 受控上下文注入与角色配置要求。
本主题/岗位 Skill 按 女娲 · Skill造人术 的主题 Skill 变体生成。
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.
- 5d ago First seen · 59 lines · 66 tokens per session scan A 59623cdb6225
devils-advocate-agent is a skill published in the GitHub repository EthanYoQ/AgentHive (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 727 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 2026-08-31.
Other skills, from other repositories
the-crucible
Run The Crucible (圆桌萃鉴), a rigorous evidence-backed multi-reviewer review. Configure a confirmed table, preserve separate first passes, mechanically compare per-item findings, adjudicate objections against primary evidence, and produce traceable consensus and unresolved decisions. Use when the user explicitly asks for…
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…