arbitration-methodology

arbitration-methodology is a skill for Claude Code, Codex from duolongworld/AI_Renaissance. It costs 129 tokens per session (3,703 once invoked), scanned A, original, Apache-2.0.

A market-signal arbitration method that chooses among bull, bear, and range-bound scenarios, then combines signals from seven expert groups using scenario-specific weights.

In plain words
What is it for?
Use it to design scenarios, set or revise signal weights, select a scenario, combine expert signals, track each contribution, and calibrate weights against historical results.
Why use it?
It provides a consistent way to handle agreement and disagreement between signals, while keeping the reasoning and weight choices traceable. It does not read raw market data or replace risk controls.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to design scenarios, set or revise signal weights, select a scenario, combine expert signals, track each contribution, and calibrate weights against historical results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/duolongworld/ai_renaissance/arbitration-methodology
Install

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.

Any agent
npx skills add duolongworld/AI_Renaissance --skill arbitration-methodology
Clone the repo
git clone --depth 1 https://github.com/duolongworld/AI_Renaissance

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for arbitration-methodology

README.md
[![agentmods](https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/arbitration-methodology/github.svg)](https://agentmods.dev/skills/duolongworld/ai_renaissance/arbitration-methodology)
Your own site
<a href="https://agentmods.dev/skills/duolongworld/ai_renaissance/arbitration-methodology"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/arbitration-methodology/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.

agentmods 80×15 button for arbitration-methodology

Your own site · 80×15
<a href="https://agentmods.dev/skills/duolongworld/ai_renaissance/arbitration-methodology"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/arbitration-methodology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,703 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00129 $0.03703
Opus 5 $0.00064 $0.01852
Sonnet 5 $0.00026 $0.00741
Haiku 4.5 $0.00013 $0.00370

Measured 10d ago against content hash b266aab33977, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

arbitration-methodology 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 10d 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.

skills/orchestrator/arbitration-methodology/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

仲裁方法论 Skill

1. 适用范围

适用任务

  • 设计或迭代三个市场场景(牛市/熊市/震荡市)的专家权重配置
  • 对 7 个专家组的 Signal 执行场景选择与加权仲裁
  • 用历史信号数据校准权重数值(理论锚定 + 实证微调)
  • 生成包含共识/分歧标注和贡献追踪的标准化推理链
  • 维护场景识别规则(match_signals)和仓位公式

边界说明

  • 本 Skill 负责场景规则定义和权重配置,不分析原始市场数据(CPI、K线、VIX 等)
  • 权重数值为"研究驱动的理论值",标注为占位初稿,后续需回测校准
  • 不替代风控层——仓位上限仅为场景建议,最终决策权在用户
  • 场景选择基于 7 个专家组的 Signal(方向 + 置信度),不读取原始行情
  • 方法论理论依据详见 references/methodology.md

2. 模式判定

触发条件 模式 说明
用户讨论权重设计、场景规则、仓位公式 模式A:场景设计与权重配置 迭代场景参数
用户要求执行仲裁、分析信号、生成推理链 模式B:信号仲裁执行 运行仲裁引擎
用户提供历史信号数据、要求校准权重 模式C:权重校准 回测校准

3. 模式A:场景设计与权重配置

当用户需要新增场景、调整权重或修改仓位公式时执行。

3.1 加载当前配置

读取以下文件了解现状:

  • agents/orchestrator/scenarios/bull_market.py
  • agents/orchestrator/scenarios/bear_market.py
  • agents/orchestrator/scenarios/range_market.py
  • references/weights.md(权重设计速查表)

3.2 变更检查清单

每次修改权重或场景规则时,逐项确认:

  • 权重方向(升/降/平)是否与桥水框架对该场景的定义一致
  • 每个权重数值是否有可追溯的研究理由(标注于 _BASE_WEIGHTS 的 reason 字段)
  • 仓位系数和上限是否符合该场景的风险特征
  • match_signals 条件是否正确反映该场景的信号特征
  • 场景风险提示是否覆盖该场景的典型风险
  • scenario_profile.py 基类接口未被破坏
  • scenario_selector.py 选择逻辑无需修改(新场景自动注册)

3.3 权重设计规则

权重方向由理论框架决定(详见 references/methodology.md):

牛市(增长↑ + 通胀↓ + 风险压缩):
  提权: 技术面、资金流、产业分析
  不变: 宏观面
  降权: 财务面、舆情组、风险面

熊市(风险溢价扩张):
  提权: 风险面、财务面、产业分析、宏观面
  降权: 资金流、舆情组、技术面

震荡市(三维度均衡):
  提权: 产业分析、风险面、资金流
  不变: 宏观面
  降权: 财务面、舆情组、技术面

具体数值见 references/weights.md

3.4 新增场景模板

新增场景需继承 ScenarioProfile 并实现 6 个方法:

class NewScenario(ScenarioProfile):
    @property
    def name(self) -> str: ...
    @property
    def display_name(self) -> str: ...
    @property
    def description(self) -> str: ...
    
    _BASE_WEIGHTS: Dict[str, Tuple[float, str]] = {...}
    
    def get_weight(self, expert_type, market_data=None) -> Tuple[float, str]: ...
    def match_signals(self, signals) -> Tuple[float, str, Dict]: ...
    def get_position_ratio(self, confidence, direction) -> Tuple[float, str]: ...
    def get_scenario_risks(self) -> List[str]: ...
    def get_confidence_threshold(self) -> Optional[float]: ...

Read the full file on GitHub · 317 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 317 lines · 129 tokens per session scan A b266aab33977

Subscribe to this mod's changes

arbitration-methodology is a skill published in the GitHub repository duolongworld/AI_Renaissance (59 stars, last pushed 13d ago), licensed Apache-2.0. It adds 129 tokens to every session and 3,703 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.

Related

Other skills, from other repositories