trading-risk-rules
Skill1 starsChanged 8 days agoMITView on GitHub
Read and change the desk's risk rules and use the kill switch. Explains what each guardrail does and which ones can never be switched off. Use when the user says "change my max loss", "set a daily limit", "more leverage", "stop everything", "kill switch", or "what are my rules".
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-paper-deskSkill
- 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, 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
- Distinctive: line 29
If the user asks to remove a guardrail, say which ones cannot be removed and why, and offer to change its value instead.
≈ “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
Risk rules
The rules live in state/rules.json. The app edits the same file through the API, and normalize() in tradedesk/risk.py enforces the floors and ceilings.
| Rule | Default | Note |
| max_loss_per_trade_usd | 30 | loss at the stop, after rounding to whole contracts |
| risk_pct | 1% | of equity; the smaller of this and the max loss wins |
| daily_loss_cap_usd | 150 | today's realized loss + open risk + the new trade must fit under it; minimum $1 |
| max_leverage | 5 | also capped per coin by the exchange's overnight limit |
| max_open_positions / max_trades_per_day | 3 / 12 | |
| news_filter + news_blackout | on, [] | UTC windows, for example {"start":"2026-12-10T18:55:00Z","end":"2026-12-10T19:30:00Z","label":"FOMC"} |
| kill_switch | off | on = close every trade and block new entries |
| live_enabled | off | needs the typed confirmation in the app |
These stay on whatever the values are:
- a stop on every order (resting on the exchange in live)
- the daily loss cap
- the loss cap per trade
- the leverage cap
- the kill switch
- stale-data protection
If the user asks to remove a guardrail, say which ones cannot be removed and why, and offer to change its value instead.
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.

