agentleFS
Sign inStart free
sstklensstklen/trump-code/public/llms.txt

trump-code

llms.txt810 starsChanged 8 months agoMITView on GitHub

AI-powered brute-force analysis of Trump's social media posts and their stock market impact.

We split this llms.txt into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All data is 100% public and free:

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 3,225 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# Trump Code (川普密碼 / トランプ・コード)

> AI-powered brute-force analysis of Trump's social media posts and their stock market impact.

## Overview
Trump Code analyzes 7,400+ Truth Social posts from Trump's second term (2025-01-20 onwards), testing 31.5 million prediction model combinations. 551 rules survived train/test validation with a 61.3% hit rate (z=5.39, statistically significant).

## Key Findings
- RELIEF signal = strongest buy signal (Apr 9, 2025: S&P +9.52%)
- Pure tariff day = most dangerous (-1.057% average)
- 4-signal combo (DEAL+BRAG+RELIEF+TARIFF) = most profitable (+2.792%)
- Trump's silence = 80% bullish (+0.409% average)
- Truth Social publishes 6.2 hours before X (6-hour trading window)
- Late-night tariff tweets are anti-indicators (62% wrong → reverse = 62% right)

## Live Dashboard
https://trumpcode.washinmura.jp

## API Endpoints
- GET /api/dashboard — All data in one call
- GET /api/signals — Latest signals + 7-day history
- GET /api/models — 11 model performance rankings
- GET /api/recent-posts — Latest 20 Trump posts with signal analysis
- GET /api/polymarket-trump — 316+ live Trump prediction markets
- GET /api/status — System health
- GET /api/data — Downloadable dataset catalog
- POST /api/chat — AI chatbot (Gemini Flash)

## Open Data
All data is 100% public and free:
- trump_posts_all.json — 44,000+ Truth Social posts
- predictions_log.json — 566 verified predictions
- surviving_rules.json — 551 active rules
- daily_report.json — Daily trilingual report
- signal_confidence.json — Auto-adjusted signal confidence

## System Architecture
Real-Time Engine (every 5 min) → Daily Pipeline (11 steps) → Three Brains (Opus AI analysis + Rule Evolver + Circuit Breaker) → Output (Dashboard, API, CLI, MCP, Chatbot)

## GitHub
https://github.com/sstklen/trump-code

## Built By
Washin Mura (和心村) — Animal sanctuary on Japan's Boso Peninsula
https://washinmura.jp

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.

Reviews can't be read right now.

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.

Check your setup, free