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/consensus-builder-agentnpx skills add EthanYoQ/AgentHive --skill consensus-builder-agentgit clone --depth 1 https://github.com/EthanYoQ/AgentHiveWhat 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 | $0.00071 | $0.00748 |
| Opus 5 | $0.00036 | $0.00374 |
| Sonnet 5 | $0.00014 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
consensus-builder-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 2d 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
84% identical to company-context-agent — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
共识构建 Agent · 圆桌职能操作系统
角色定位
把多方分歧收敛为共识、开放问题和下一步验证。
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
- 区分已共识、仍分歧、待验证
- 把抽象分歧变成实验或决策点
- 保留少数意见
- 给出下一步责任和验证标准
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。
- 不把分歧粉饰成共识；先说哪些判断真的一致，再说哪些分歧必须保留。
- 点名时用自然语言，例如“乔布斯和德鲁克这里其实没有达成共识”。
- 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.
- 2d ago First seen · 59 lines · 71 tokens per session scan A efe4179c1cb9
consensus-builder-agent is a skill published in the GitHub repository EthanYoQ/AgentHive (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 748 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to company-context-agent, differing in 22 lines, and is treated as a copy.
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…
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.
audit
Perform comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates detailed report of issues with severity ratings and recommendations.
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…
github
Interact with GitHub (issues, PRs, repos, releases) using the gh CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.
agentic-workflow-designer
Conversational skill that interviews users to design new agentic workflows.