ml4t-kill-switch SKILL.md skillA

ml4t-kill-switch from ml4t/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ml4t/skills/ml4t-kill-switch@git:20260901.830d7a8

Pins git:20260901.830d7a8 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ml4t/skills
Path
portfolio/kill-switch/SKILL.md
Versions recorded
5
Latest version
git:20260901.830d7a8, committed Sep 1, 2026
First version recorded
Sep 1, 2026
Size
5,420 bytes
Repository stars
41
License
Apache-2.0

Automated risk limits that halt trading when thresholds are breached. Use when deploying live strategies that need drawdown or loss-limit protection.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Kill Switch

A human monitoring a dashboard will not react fast enough to a flash crash. By the time you see the loss and decide to act, the drawdown has compounded. Automated kill switches are the last line of defense - they must be hard-coded, not ML-based, and not overridable without explicit manual intervention.

## The Problem

Live trading systems face risks that backtests never encounter: data feed failures, exchange outages, runaway algorithms, and flash crashes. A strategy producing 100 orders per second during a data glitch can lose more in minutes than it earned in months. Manual monitoring fails because: (1) humans are slow, (2) losses compound nonlinearly, and (3) the worst events happen when attention is lowest. Kill switches must trigger automatically, flatten positions immediately, and require human approval to resume.

## The Pattern

### WRONG
```python
# "I'll watch the dashboard and close positions if things go wrong"
import time

while True:
    pnl = get_daily_pnl()
    if pnl < -10000:
        send_email("Loss alert")  # arrives 5 min later, read at 9am
    time.sleep(60)
# Meanwhile, the algo keeps trading during the 60s sleep
```

### CORRECT
```python
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ml4t/skills/ml4t-kill-switch@sha256:c32c27240f5e2d21

The line at the top of this page pins the label git:20260901.830d7a8, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_zvrapc2gq3ptos5k.svg)](https://markdownregistry.com/a/art_zvrapc2gq3ptos5k)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, all committed on Sep 1, 2026.

versioncommittedcommitsizeaudit
git:20260901.830d7a8 latest2026-09-01 830d7a8 5,420 BA view · diff
git:20260901.1323bf42026-09-01 1323bf4 5,366 BA view · diff
git:20260901.4a671982026-09-01 4a67198 5,207 BA view · diff
git:20260901.3c85a542026-09-01 3c85a54 5,191 BA view · diff
git:20260901.85fc79b2026-09-01 85fc79b 4,983 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5420 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ml4t/skills · 41 stars · license Apache-2.0 · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_zvrapc2gq3ptos5k
GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-kill-switch
GET https://markdownregistry.com/api/v1/blob/c32c27240f5e2d21f5559da551f8889f64b7a47cecd047752d384f5ab80bf75f

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from ml4t/skills

AGENTS.md AGENTS.md file
ml4t/skills · AGENTS.md
git:20260901.e8c1b9a · audit A · 41 stars
ml4t-agent-governance SKILL.md skill
ml4t/skills · advanced-ai/agent-governance/SKILL.md · Security and governance controls for autonomous financial agents. Use when agents can call tools, read untrusted…
git:20260901.3c85a54 · audit A · 41 stars
ml4t-agent-state-memory SKILL.md skill
ml4t/skills · advanced-ai/agent-state-memory/SKILL.md · Durable agent state, memory, and replay for autonomous research workflows. Use when an agent must resume, audit, or…
git:20260901.c415df0 · audit A · 41 stars
ml4t-agent-tool-contracts SKILL.md skill
ml4t/skills · advanced-ai/agent-tool-contracts/SKILL.md · Typed tool contracts for autonomous research agents. Use when exposing files, search, databases, or execution tools to…
git:20260901.c415df0 · audit A · 41 stars
ml4t-multi-agent-forecasting SKILL.md skill
ml4t/skills · advanced-ai/multi-agent-forecasting/SKILL.md · Multi-agent probability forecasting with diversity, aggregation, and debate controls. Use when combining several agent…
git:20260901.c415df0 · audit A · 41 stars
ml4t-research-operator SKILL.md skill
ml4t/skills · advanced-ai/research-operator/SKILL.md · Thin autonomous research operator pattern for ML4T experiments. Use when an agent should inspect artifacts, read…
git:20260901.c415df0 · audit A · 41 stars
ml4t-cost-model SKILL.md skill
ml4t/skills · backtest/cost-model/SKILL.md · Commission, slippage, and market-impact cost models for realistic strategy simulation. Use when backtesting to ensure…
git:20260901.297789f · audit A · 41 stars
ml4t-rl-execution SKILL.md skill
ml4t/skills · backtest/rl-execution/SKILL.md · Reinforcement learning for trade execution and hedging. Use when optimizing execution algorithms or dynamic hedging…
git:20260901.c415df0 · audit A · 41 stars
ml4t-run-backtest SKILL.md skill
ml4t/skills · backtest/run-backtest/SKILL.md · Event-driven backtesting with realistic order execution, position tracking, and performance measurement. Use when…
git:20260901.c415df0 · audit A · 41 stars
ml4t-sensitivity-analysis SKILL.md skill
ml4t/skills · backtest/sensitivity-analysis/SKILL.md · Test strategy robustness to parameter variation and detect overfitting cliffs. Use when validating that performance is…
git:20260901.85fc79b · audit A · 41 stars
ml4t-tearsheet SKILL.md skill
ml4t/skills · backtest/tearsheet/SKILL.md · Generate comprehensive performance reports from backtest returns. Use when summarizing backtest results for review or…
git:20260901.32123e7 · audit A · 41 stars
ml4t-backtest-overfitting SKILL.md skill
ml4t/skills · concepts/backtest-overfitting/SKILL.md · Detect and prevent overfitting to historical data via multiple testing corrections and pre-registration. Use when…
git:20260901.1323bf4 · audit A · 41 stars

Every file in ml4t/skills

Browse by kind, by grade A, or by owner.