trading-paper-desk
Skill1 starsChanged 8 days agoMITView on GitHub
Run the forward-test and paper-trading desk on the user's PC and connect the phone dashboard over Tailscale. Use when the user says "start paper trading", "run the bot", "keep it running", "connect my phone", "the app shows demo data", or "set it up on my old PC".
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms.txtllms.txt
- trading-backtestSkill
- trading-deskSkill
- trading-go-liveSkill
- trading-learnSkill
- trading-risk-rulesSkill
- trading-rotationSkill
- trading-strategy-labSkill
- trading-venuesSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
Create a random token and save it as the user environment variable TRADEDESK_API_TOKEN, without printing it in chat.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill 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.
Files
Paper desk and phone link
What runs
python -m tradedesk desk: every 30 seconds it pulls closed 5-minute Coinbase perp candles (public data), runs every strategy at stage forward or above, manages positions, and journals everything tostate/journal.sqlite.- forward: signals, with simulated outcomes
- paper: a simulated account funded with
rules.paper_equity_usd
python -m tradedesk serve --host <tailscale-ip>: the phone API. It needsTRADEDESK_API_TOKEN(24 or more random characters) in the environment.
Always-on PC (Windows)
The private dashboard repo has desk/setup.ps1 and desk/install-tasks.ps1, which do steps 2 and 4.
- Install Python 3.10+ and clone this repo on the PC.
- Create a random token and save it as the user environment variable
TRADEDESK_API_TOKEN, without printing it in chat. The user reads it on the PC and types it into the app. - Install Tailscale on the PC and the phone, signed into the same account. MagicDNS gives the PC a name like
pc-name.tailXXXX.ts.net. - Register
deskandserveas scheduled tasks that run at log-on and restart if they fail. - In the app, open Rules > Connection and enter
http://pc-name.tailXXXX.ts.net:8787and the token.
Health
python -m tradedesk status shows the ladder, the open trades and the latest events. If data goes stale (no new bar for 15 minutes), the desk opens no new trades.
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
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.

