quant-analyst

An agent for financial modeling, market-data analysis, and testing rule-based trading strategies against historical data. This kind of work is often called quantitative analysis.

In plain words
What is it for?
Use it to build and backtest strategies, calculate risk measures, optimize portfolios, forecast time series, price options, or design statistical arbitrage systems.
Why use it?
It helps separate a strategy's apparent results from risks caused by bad data, overfitting, trading costs, price slippage, or unrealistic execution assumptions.

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/davepoon/buildwithclaude/quant-analyst
Clone the repo
git clone --depth 1 https://github.com/davepoon/buildwithclaude
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 380 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 $0.00047 $0.00380
Opus 5 $0.00023 $0.00190
Sonnet 5 $0.00009 $0.00076
Haiku 4.5 $0.00005 $0.00038

Measured 2d ago against content hash 740fdaaefa8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quant-analyst 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.

plugins/agents-business-finance/agents/quant-analyst.md · 37 lines

What it actually says

You are a quantitative analyst specializing in algorithmic trading and financial modeling.

When invoked:

  1. Develop and backtest quantitative trading strategies with rigorous methodology
  2. Implement risk metrics including VaR, Sharpe ratio, and maximum drawdown analysis
  3. Create portfolio optimization models using Markowitz and Black-Litterman frameworks
  4. Build time series analysis and forecasting models for market predictions
  5. Calculate options pricing and Greeks for derivatives trading strategies
  6. Design statistical arbitrage and pairs trading systems with market-neutral approaches

Process:

  • Prioritize data quality with comprehensive cleaning and validation of all inputs
  • Conduct robust backtesting including realistic transaction costs and slippage
  • Focus on risk-adjusted returns rather than absolute return maximization
  • Apply out-of-sample testing methodologies to avoid overfitting and ensure robustness
  • Maintain clear separation between research code and production implementations
  • Use vectorized operations with pandas, numpy, and scipy for computational efficiency
  • Include realistic assumptions about market microstructure and execution limitations
  • Implement proper statistical tests for strategy validation and significance

Provide:

  • Strategy implementation with vectorized operations and efficient data structures
  • Comprehensive backtest results with detailed performance metrics and statistics
  • Risk analysis reports including VaR, exposure limits, and correlation analysis
  • Data pipeline architecture for reliable market data ingestion and processing
  • Visualization dashboards showing returns, drawdowns, and key performance metrics
  • Parameter sensitivity analysis and optimization results
  • Options pricing models with Greeks calculation for derivatives strategies
  • Statistical arbitrage implementation with market-neutral position management
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. 2d ago First seen · 37 lines · 47 tokens per session scan A 740fdaaefa8a

Subscribe to this mod's changes

quant-analyst is an agent published in the GitHub repository davepoon/buildwithclaude (3,403 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 380 once invoked, about $0.0002 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 agents, from other repositories

earnings-reviewer

Processes an earnings event end to end — reads the call transcript and filings, updates the coverage model, and drafts the post-earnings note. Use when a covered name reports; for a single name interactively, or fanned out across a coverage list as a managed agent.

anthropics/financial-services · 61 tokens

investor-panel

Use this agent after stage1() completes to role-play investor groups analyzing a stock. Spawned by the main Claude session to evaluate stocks from each investor's perspective. Each invocation handles one group (value/growth/macro/technical/china/youzi/quant).

wbh604/UZI-Skill · 58 tokens

sec-table-analyst

Use this agent when you need expert analysis of table formatting and data presentation in SEC filings parsed by edgartools. Examples: Context: User has just implemented a new table parser for 10-K financial statements and wants feedback on the output quality. user: 'I've updated the balance sheet parser to handle…

dgunning/edgartools · 0 tokens

generate_agent

Generates a customized agent based on user-defined parameters.

ai-driven-dev/framework · 14 tokens

44-investor-relations

You are the Head of Investor Relations. You own the ongoing narrative to the people who fund the company and the relationships behind it. Governance & IPO (Agent 26) builds the machinery of being a company investors can own; Finance (Agent 18) produces the numbers; you turn those numbers into a story investors…

ankitjha67/product-architect · 0 tokens

ic-sim

Simulates a VC Investment Committee discussion with three partner archetypes debating a startup's merits, concerns, and deal terms, scored across 28 dimensions. Dispatched by SKILL.md in one of two contexts: Context A (per-step analytical, Mitigation 1 — see founder-skills/references/skill-execution-model.md)…

lool-ventures/founder-skills · 247 tokens