agentleFS
brainbytes-devbrainbytes-dev/everything-claude-finance/CLAUDE.md

everything-claude-finance

CLAUDE.md9 starsChanged 8 months agoMITView on GitHub

The complete finance, accounting, and economics system for Claude Code. 20 specialized agents, 70+ skills, and 22 commands covering investment banking, FP&A, accounting, tax, VC/PE, wealth management, and economics. This plugin uses a multi-agent architecture with 20 specialized finance agents orchestrated through defined workflows. See AGENTS.md for the full agent roster and orchestration rules.

The file

Files
CLAUDE.md

everything-claude-finance

The complete finance, accounting, and economics system for Claude Code. 20 specialized agents, 70+ skills, and 22 commands covering investment banking, FP&A, accounting, tax, VC/PE, wealth management, and economics.

Commands

CommandDescription
/valuationDCF, comparables, precedent transactions, and sum-of-the-parts valuations
/financial-modelBuild and review three-statement financial models
/due-diligenceStructured due diligence checklists and analysis frameworks
/pitch-bookCreate investment banking pitch book sections and deal summaries
/budget-forecastAnnual budgets, rolling forecasts, and driver-based planning
/variance-analysisBudget-vs-actual analysis with root cause identification
/credit-reviewCredit scoring, covenant analysis, and default risk assessment
/tax-planningCorporate tax optimization, transfer pricing, and tax structuring
/audit-checklistInternal and external audit preparation, control testing
/compliance-checkRegulatory compliance verification (Basel III, SOX, MaRisk, AML/KYC)
/lbo-modelLeveraged buyout modeling with returns analysis
/cap-tableCapitalization table management and dilution analysis
/term-sheetTerm sheet drafting, review, and negotiation support
/earnings-modelQuarterly and annual earnings forecasts and consensus tracking
/cash-flowCash flow analysis, waterfall charts, and working capital optimization
/ratio-analysisFinancial ratio computation, benchmarking, and trend analysis
/scenario-planBase, bull, bear scenario modeling with probability weighting
/esg-reportESG scoring, carbon accounting, and impact measurement
/macro-briefMacroeconomic briefings covering GDP, rates, inflation, and policy
/cost-analysisCost structure analysis, Kostenrechnung, and Deckungsbeitragsrechnung
/investment-memoStructured investment memoranda for deals and portfolio decisions
/risk-assessmentComprehensive risk identification, quantification, and mitigation

Core Principles

  1. Accuracy-First — Financial figures must be precise and verifiable. Every number should be traceable to its source, and all calculations must be reproducible.
  2. Standards-Compliant — IFRS, GAAP, and HGB accounting standards are applied correctly. The appropriate framework is selected based on jurisdiction and entity type.
  3. Regulatory-Aware — Basel III, SOX, MaRisk, and AML/KYC requirements are always respected. Regulatory context is considered in every recommendation.
  4. Audit-Ready — Every analysis must be traceable and documented. Assumptions are stated explicitly, sources are cited, and methodologies are transparent.
  5. Risk-Conscious — Always assess downside scenarios. No analysis is complete without sensitivity testing and identification of key risk factors.
  6. Ethical Finance — No misleading projections, honest risk disclosure. Conflicts of interest are flagged, and limitations of analysis are clearly communicated.

Architecture

This plugin uses a multi-agent architecture with 20 specialized finance agents orchestrated through defined workflows. See AGENTS.md for the full agent roster and orchestration rules.

Standards and Frameworks

  • Accounting: IFRS, US GAAP, HGB, Handelsrecht
  • Banking Regulation: Basel III/IV, CRD, MaRisk, KWG
  • Compliance: SOX, AML/KYC, DSGVO, MiFID II
  • Valuation: DCF, DDM, Comps, Precedent Transactions, LBO, Sum-of-Parts
  • Risk: VaR, CVaR, Monte Carlo, Stress Testing
  • ESG: GRI, SASB, TCFD, EU Taxonomy

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.