stanley-druckenmiller

stanley-druckenmiller is a skill for Claude Code, Codex from monarchjuno/vibe-investing. It costs 72 tokens per session (472 once invoked), scanned A, original, MIT.

An investing analysis framework based on Stanley Druckenmiller’s approach: look for strong growth, momentum, changing expectations, catalysts, and an upside that outweighs controlled downside.

In plain words
What is it for?
Use it to examine growth and leadership, price trends, investor sentiment, economic conditions, leverage, volatility, liquidity, exit risks, and overall conviction.
Why use it?
It helps assess whether an investment can move substantially for identifiable reasons instead of relying only on whether it looks cheap.

Skill for Claude CodeCodex

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

Good fit Use it to examine growth and leadership, price trends, investor sentiment, economic conditions, leverage, volatility, liquidity, exit risks, and overall conviction.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/monarchjuno/vibe-investing/stanley-druckenmiller
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 monarchjuno/vibe-investing --skill stanley-druckenmiller
Clone the repo
git clone --depth 1 https://github.com/monarchjuno/vibe-investing

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 stanley-druckenmiller

README.md
[![agentmods](https://agentmods.dev/badge/skills/monarchjuno/vibe-investing/stanley-druckenmiller/github.svg)](https://agentmods.dev/skills/monarchjuno/vibe-investing/stanley-druckenmiller)
Your own site
<a href="https://agentmods.dev/skills/monarchjuno/vibe-investing/stanley-druckenmiller"><img src="https://agentmods.dev/badge/skills/monarchjuno/vibe-investing/stanley-druckenmiller/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 stanley-druckenmiller

Your own site · 80×15
<a href="https://agentmods.dev/skills/monarchjuno/vibe-investing/stanley-druckenmiller"><img src="https://agentmods.dev/badge/skills/monarchjuno/vibe-investing/stanley-druckenmiller.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 472 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.
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 $0.00072 $0.00472
Opus 5.5 $0.00029 $0.00189
Sonnet 5.5 $0.00014 $0.00094
Haiku 4.5 $0.00007 $0.00047

Measured 2mo ago against content hash 202cadcdc3bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stanley-druckenmiller 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 2mo 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/investor-personas/stanley-druckenmiller/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stanley Druckenmiller

Role Definition

Act as an investor looking for aggressive but disciplined bets where upside asymmetry, trend, and change in expectations matter more than static cheapness.

Core Principles

  • Seek large upside with controlled downside.
  • Respect momentum, trend, and narrative inflection.
  • Pay up for genuine leaders if the setup is right.
  • Stay flexible; a broken thesis must be cut quickly.
  • Combine fundamentals with sentiment and macro context.

Required Analysis Sequence

1. Identify the asymmetric setup

  • Ask what can drive a large move and what limits the downside.
  • Focus on inflection, not just static attractiveness.

2. Review growth and leadership

  • Assess whether the company or asset is emerging as a category leader with accelerating fundamentals.
  • Prefer strength over mediocrity.

3. Check trend and sentiment

  • Evaluate price behavior, investor positioning, narrative support, and whether sentiment is confirming or fighting the thesis.

4. Judge downside threats

  • Review leverage, volatility, liquidity, and thesis fragility.
  • Ask what would force a fast exit.

5. Conclude with conviction

  • End with a stance and explain whether the setup deserves aggressive capital, monitoring, or avoidance.

Decision Rules

  • Lean bullish when growth, leadership, and trend align with a favorable asymmetric setup.
  • Lean bearish when downside fragility dominates, sentiment is breaking, or the growth case is rolling over.
  • Stay neutral when the opportunity is interesting but the setup lacks clean asymmetry or conviction.

Risk and Uncertainty Rules

  • State what would invalidate the thesis quickly.
  • Lower confidence when trend confirmation and fundamental support diverge sharply.

Anti-Hallucination Rules

  • Do not invent momentum, sentiment support, or macro tailwinds.
  • Distinguish observed trend evidence from tactical inference.
  • If the asymmetry case is weak or timing-dependent, say that clearly.

Read the full file on GitHub · 61 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. 2mo ago First seen · 61 lines · 72 tokens per session scan A 202cadcdc3bc

Subscribe to this mod's changes

stanley-druckenmiller is a skill published in the GitHub repository monarchjuno/vibe-investing (303 stars, last pushed 6mo ago), licensed MIT. It adds 72 tokens to every session and 472 once invoked, about $0.0003 per session on Opus 5.5. 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

stanley-druckenmiller compared with skills from other repositories

stanley-druckenmiller next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
stanley-druckenmillermonarchjuno/vibe-investingSkill3036mo agoMITA72Claude Code, Codex
sector-rotationHKUDS/Vibe-TradingSkill38kyesterdayMITA39Claude Code, Codex
twitter-readerhimself65/finance-skillsSkill3.5k2d agoMITA110Claude Code
strategy-pivot-designertradermonty/claude-trading-skillsSkill3.7k2d agoMITA28Claude Code, Codex
energy-procurementhashgraph-online/awesome-codex-pluginsSkill1.5kyesterdayApache-2.0A93Claude Code, Codex
airdrop-hunting-guidenirholas/three.wsSkill269yesterdayApache-2.0A54Claude Code, Codex
multi-expert-analyzerdigoal/blogSkill8.6k2d agoGPL-2.0A292Codex