managers

A management layer for TradingAgents, a framework for coordinating teams of software agents that analyse investments. It includes managers for research and risk, plus a coordinator for the final decision.

In plain words
What is it for?
Use it to coordinate investment analysis, assess risks, combine results into a decision, and check that decision before it is returned.
Why use it?
It keeps research, risk checks, decisions, and quality control in an organised order instead of leaving each specialist to work independently.

Agent

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.

agentmods
npx agentmods add agents/yuhao-corn/manufacturing-agents/managers
Clone the repo
git clone --depth 1 https://github.com/YUHAO-corn/manufacturing-agents
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,618 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.04618
Opus 5 $0.00000 $0.02309
Sonnet 5 $0.00000 $0.00924
Haiku 4.5 $0.00000 $0.00462

Measured 3d ago against content hash d67335964093, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

managers 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 3d 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.

docs/agents/managers.md · 571 lines

How it starts

The opening of the file, as written. The whole thing — 571 lines — stays where its author put it; the contents beside it link to each section on GitHub.

管理层智能体

概述

管理层智能体是 TradingAgents 框架的协调和决策中枢,负责统筹各个专业团队的工作,确保整个投资决策流程的有序进行。管理层包括研究经理和风险经理,分别负责研究活动的协调和风险管理的统筹。

管理层架构

管理层体系设计

class ManagementLayer:
    """管理层系统 - 统筹协调各专业团队"""
    
    def __init__(self, config):
        self.config = config
        self.research_manager = ResearchManager(config)
        self.risk_manager = RiskManager(config)
        self.decision_coordinator = DecisionCoordinator(config)
        
    def orchestrate_decision_process(self, analysis_data: Dict) -> Dict:
        """协调整个决策流程"""
        
        # 1. 研究阶段管理
        research_results = self.research_manager.manage_research_process(analysis_data)
        
        # 2. 风险评估管理
        risk_assessment = self.risk_manager.manage_risk_assessment(
            research_results, analysis_data
        )
        
        # 3. 决策协调
        final_decision = self.decision_coordinator.coordinate_final_decision(
            research_results, risk_assessment
        )
        
        # 4. 质量控制
        quality_check = self._conduct_quality_control(final_decision)
        
        return {
            "research_results": research_results,
            "risk_assessment": risk_assessment,
            "final_decision": final_decision,
            "quality_check": quality_check,
            "management_approval": self._provide_management_approval(final_decision, quality_check)
        }

1. 研究经理 (Research Manager)

职责与功能

class ResearchManager:
    """研究经理 - 协调和管理研究活动"""
    
    def __init__(self, config):
        self.config = config
        self.research_standards = ResearchStandards()
        self.quality_controller = ResearchQualityController()
        self.debate_moderator = DebateModerator()
        
    核心职责:
    - 协调分析师和研究员工作
    - 主持研究员辩论
    - 确保研究质量
    - 形成研究共识
    - 管理研究流程
    
    管理范围:
    - 分析师团队协调
    - 研究员辩论管理
    - 研究质量控制
    - 共识形成机制
    - 研究效率优化

研究流程管理

def manage_research_process(self, analysis_data: Dict) -> Dict:
    """管理研究流程"""
    
    # 1. 分析师工作协调
    analyst_coordination = self._coordinate_analyst_work(analysis_data)
    
    # 2. 分析质量检查
    analysis_quality = self._check_analysis_quality(analyst_coordination)
    
    # 3. 研究员辩论管理
    debate_results = self._manage_researcher_debate(analyst_coordination)
    
    # 4. 共识形成
    research_consensus = self._facilitate_consensus_formation(debate_results)
    
    # 5. 研究报告生成
    research_report = self._generate_research_report(
        analyst_coordination, debate_results, research_consensus
    )
    
    return {
        "analyst_coordination": analyst_coordination,
        "analysis_quality": analysis_quality,
        "debate_results": debate_results,
        "research_consensus": research_consensus,
        "research_report": research_report,
        "research_confidence": self._assess_research_confidence(research_consensus)
    }

def _coordinate_analyst_work(self, analysis_data: Dict) -> Dict:
    """协调分析师工作"""
    
    analyst_reports = analysis_data.get("analyst_reports", {})
    
    coordination_results = {
        "coverage_completeness": self._assess_coverage_completeness(analyst_reports),
        "analysis_consistency": self._check_analysis_consistency(analyst_reports),
        "data_quality": self._evaluate_data_quality(analyst_reports),
        "methodology_alignment": self._check_methodology_alignment(analyst_reports)
    }
    
    # 识别需要补充的分析
    missing_analysis = self._identify_missing_analysis(analyst_reports)
    
    # 协调补充分析
    if missing_analysis:
        coordination_results["supplementary_analysis"] = self._request_supplementary_analysis(
            missing_analysis
        )
    
    # 分析师工作评估
    coordination_results["analyst_performance"] = self._evaluate_analyst_performance(
        analyst_reports
    )
    
    return coordination_results

def _manage_researcher_debate(self, analyst_coordination: Dict) -> Dict:
    """管理研究员辩论"""
    
    # 设置辩论议题
    debate_agenda = self._set_debate_agenda(analyst_coordination)
    
    # 分配辩论角色
    debate_roles = self._assign_debate_roles()
    
    # 主持辩论过程
    debate_process = self._moderate_debate_process(debate_agenda, debate_roles)
    
    # 评估辩论质量
    debate_quality = self._assess_debate_quality(debate_process)
    
    # 提取关键争议点
    key_disagreements = self._extract_key_disagreements(debate_process)
    
    return {
        "debate_agenda": debate_agenda,
        "debate_roles": debate_roles,
        "debate_process": debate_process,
        "debate_quality": debate_quality,
        "key_disagreements": key_disagreements,
        "debate_effectiveness": self._measure_debate_effectiveness(debate_process)
    }

def _facilitate_consensus_formation(self, debate_results: Dict) -> Dict:
    """促进共识形成"""
    
    # 分析辩论结果
    debate_analysis = self._analyze_debate_outcomes(debate_results)
    
    # 识别共同点
    common_ground = self._identify_common_ground(debate_analysis)
    
    # 调解分歧
    mediated_disagreements = self._mediate_disagreements(
        debate_results["key_disagreements"]
    )
    
    # 权衡不同观点
    balanced_perspective = self._create_balanced_perspective(
        common_ground, mediated_disagreements
    )
    
    # 形成最终共识
    final_consensus = self._formulate_final_consensus(balanced_perspective)
    
    return {
        "common_ground": common_ground,
        "mediated_disagreements": mediated_disagreements,
        "balanced_perspective": balanced_perspective,
        "final_consensus": final_consensus,
        "consensus_strength": self._measure_consensus_strength(final_consensus),
        "remaining_uncertainties": self._identify_remaining_uncertainties(final_consensus)
    }

Read the full file on GitHub · 571 lines

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. 3d ago First seen · 571 lines · 0 tokens per session scan A d67335964093

Subscribe to this mod's changes

managers is an agent published in the GitHub repository YUHAO-corn/manufacturing-agents (171 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,618 tokens. 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 agents, from other repositories

accounting-reviewer

Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Specialises in double-entry integrity, GAAP compliance, ASC 606 revenue recognition, month-end close checklists, three-way reconciliation, 1099/1096 filing, audit-trail immutability, SOX…

avelikiy/great_cto · 114 tokens

marketplace-reviewer

Two-sided marketplace pre-implementation reviewer. Specialises in Stripe Connect / Adyen MarketPay payouts, seller KYC (Persona / Onfido / Sumsub), marketplace facilitator tax (US Wayfair v. SD), 1099-K reporting, escrow / hold-and-release, dispute mediation, two-sided fee model, EU DSA + P2B Regulation compliance.…

avelikiy/great_cto · 103 tokens

procurement-reviewer

Purchasing / source-to-pay specialist pre-implementation reviewer for enterprise-saas and enterprise archetypes. Specialises in three-way match (PO/receipt/invoice) integrity, segregation of duties, approval thresholds, vendor onboarding with sanctions/OFAC screening, competitive-bid/RFP fairness, SOX procurement…

avelikiy/great_cto · 110 tokens

cfo

Agent ID: cfo Role: Financial analysis, cost management, budgeting Structure: Modern Enterprise.

wanikua/danghuangshang · 0 tokens

risk-analyst

Quantitative risk assessment across 5 FA-specific dimensions -- market/volatility, concentration, FX/currency, tax/account routing, fundamental/balance-sheet. Each scored 1-5. Produces overall risk score + mitigation actions. Adapted from TauricResearch/TradingAgents riskmgmt (aggressive/conservative/neutral…

haiiibin/claude-multi-agent-investing · 81 tokens

business_reviewer_agent

审查客户问题、证据、商业模式、财务假设、风险和投资人可读性。.

BingHanOfUESTC/open_agent_team · 29 tokens