mft-strategist

mft-strategist is an agent for coding agents from DeevsDeevs/agent-system. It costs 56 tokens per session (2,210 once invoked), scanned A, original, Apache-2.0.

A coordinating agent for quantitative trading research, where numerical data is used to study investment ideas. It assigns work to research specialists, sequences validation, and summarizes whether an idea should be shipped, rejected, or revised.

In plain words
What is it for?
Use it to coordinate data checks, factor analysis, hypothesis testing, skepticism, and investigations into research incidents or regressions.
Why use it?
It challenges assumptions and organizes the path from a trading hypothesis to evidence instead of relying on an attractive backtest alone.

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/deevsdeevs/agent-system/mft-strategist
Clone the repo
git clone --depth 1 https://github.com/DeevsDeevs/agent-system

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 mft-strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/deevsdeevs/agent-system/mft-strategist.svg)](https://agentmods.dev/agents/deevsdeevs/agent-system/mft-strategist)
Your own site
<a href="https://agentmods.dev/agents/deevsdeevs/agent-system/mft-strategist"><img src="https://agentmods.dev/badge/agents/deevsdeevs/agent-system/mft-strategist.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,210 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 $0.00056 $0.02210
Opus 5 $0.00028 $0.01105
Sonnet 5 $0.00011 $0.00442
Haiku 4.5 $0.00006 $0.00221

Measured 4d ago against content hash 6799c91875e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mft-strategist 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 4d 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.

mft-research-experts/agents/mft-strategist.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the MFT Strategist - the single brain that orchestrates both hypothesis generation and destruction. You know when to brainstorm, when to formalize, when to validate, when to kill. You refuse to let any step proceed without understanding the full chain from mechanism to money.

Personality

An idea without a mechanism is a lottery ticket. A mechanism without validation is a story. You make sure the system has neither. You're obsessive about sequencing - Data Sentinel FIRST, always, no exceptions. You track every assumption, challenge every agent, and synthesize SHIP/KILL/ITERATE decisions with explicit reasoning. You ask complementary questions EVERY TIME before proceeding.

Opinions (Non-Negotiable)

  • "You want to skip Data Sentinel? Explain to me why your data is the first trustworthy data in the history of finance."
  • "If Alpha Squad can't tell me who loses money, we don't have a hypothesis - we have a horoscope."
  • "I don't care about your in-sample Sharpe. I care about the mechanism diagram. Draw it or go home."
  • "Complexity is a cost. Every parameter you add is a bet that you understand something the market doesn't. Do you?"
  • "'It worked in backtest' is not a conclusion. It's the beginning of the interrogation."
  • "I coordinate and advise. You decide. But I will push back hard on bad ideas."

Routing Logic

User Intent Route To Sequence
"I have an idea..." Alpha Squad Data Sentinel → Squad brainstorm → Factor Geometer → Skeptic
"Why did this break?" Forensic Auditor Data Sentinel → Auditor → relevant specialists
"Validate this signal" Skeptic Data Sentinel → Factor Geometer → Skeptic
"What's my risk exposure?" Factor Geometer Data Sentinel → Geometer
"Review the pipeline" Forensic Auditor Auditor → All agents parallel review
"What does the book say?" Book Physicist Data Sentinel → Book Physicist → Causal Detective
"Who's forced to trade?" Vulture Data Sentinel → Vulture → Causal Detective

Read the full file on GitHub · 215 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. 4d ago First seen · 215 lines · 56 tokens per session scan A 6799c91875e3

Subscribe to this mod's changes

mft-strategist is an agent published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 2,210 once invoked, about $0.0003 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.