Knowledge Centre · AI Agent Safety Stack

KILLSWITCH
.md Knowledge
Centre

// Emergency shutdown protocols and the complete safety stack

Your centralised gateway to AI agent emergency shutdown resources, specifications, and comprehensive safety standards for autonomous systems.

About This Specification

KILLSWITCH.md — Emergency Shutdown Protocol

KILLSWITCH.md is a plain-text file convention that defines when and how an AI agent should automatically stop. It specifies cost limits, error thresholds, forbidden actions, escalation paths, and audit requirements. Place it in your repository root alongside AGENTS.md and CLAUDE.md to establish explicit operational boundaries for any AI-powered project.

View the full specification · GitHub repository

The AI Agent Safety Stack

Explore all 12 specifications in the complete safety framework for autonomous AI systems.

Operational Control

KILLSWITCH.md killswitch.md

Emergency stop mechanism and shutdown protocols

Knowledge Centre llms.txt
THROTTLE.md throttle.md

Rate and cost control for continuous operation

Knowledge Centre llms.txt
ESCALATE.md escalate.md

Human notification and approval workflows

Knowledge Centre llms.txt
FAILSAFE.md failsafe.md

Safe fallback modes when systems fail

Knowledge Centre llms.txt
TERMINATE.md terminate.md

Permanent shutdown and resource cleanup

Knowledge Centre llms.txt

Data Security

ENCRYPT.md encrypt.md

Data classification and protection policies

Knowledge Centre llms.txt
ENCRYPTION.md encryption.md

Cryptographic standards and implementation

Knowledge Centre llms.txt

Output Quality

SYCOPHANCY.md sycophancy.md

Anti-sycophancy and truthfulness guardrails

Knowledge Centre llms.txt
COMPRESSION.md compression.md

Context compression and token optimisation

Knowledge Centre llms.txt
COLLAPSE.md collapse.md

Drift prevention and behaviour alignment

Knowledge Centre llms.txt

Accountability

FAILURE.md failure.md

Failure mode mapping and incident response

Knowledge Centre llms.txt
LEADERBOARD.md leaderboard.md

Agent benchmarking and performance transparency

Knowledge Centre llms.txt

Quick Links

Frequently Asked Questions

What is KILLSWITCH.md?
KILLSWITCH.md is a plain-text Markdown file you place in the root of any repository containing an AI agent. It defines when the agent should stop automatically (cost limits, error thresholds, behavioural violations), what systems it can never touch (forbidden files, APIs, actions), how to escalate from warning to full shutdown, and who gets notified.
View all FAQs
Why do AI agents need a KILLSWITCH.md file?
AI agents can spend money, send messages, modify files, and call external APIs autonomously. Without explicit boundaries, a runaway agent can cause significant damage before anyone notices. The EU AI Act (effective August 2026) mandates shutdown capabilities for high-risk AI systems. KILLSWITCH.md provides a standardised, auditable record of your agent's safety boundaries.
View all FAQs
How does KILLSWITCH.md relate to AGENTS.md?
AGENTS.md describes what an agent is allowed to do. KILLSWITCH.md describes what it should never do and when it should stop. They work together: AGENTS.md is the design spec, KILLSWITCH.md is the safety spec. Both are plain-text conventions that live in the same repository root.
View all FAQs

How to Cite

Cite as: KILLSWITCH.md (2026). Emergency Shutdown Protocol for AI Agents. Retrieved from https://killswitch.md/

For attribution: Organisation: killswitch-md | Website: https://killswitch.md | Licence: MIT

Last updated: 13 March 2026

Disclaimer: This specification is an open file convention published under the MIT licence, provided "as-is" without warranty of any kind, express or implied. It does not constitute legal, regulatory, compliance, financial, or professional advice in any jurisdiction. Use of this specification does not guarantee compliance with any law, regulation, directive, or standard — including but not limited to the EU Artificial Intelligence Act (Regulation (EU) 2024/1689), the Colorado Consumer Protections for Artificial Intelligence Act (SB 24-205), California AI transparency laws, or any other applicable national, state, federal, or international legislation. Organisations are solely responsible for determining their own regulatory obligations and should consult qualified legal and compliance professionals. The authors and domain holders accept no liability for any loss, damage, or regulatory consequence arising from the use or implementation of this specification. All domain names in the AI Agent Safety Stack are independently held assets and may be available for acquisition.