agent-instinct-system
CommunityPrevent risky AI actions with reflex safety checks.
Software Engineering#agent safety#protected files#budget enforcement#pre-action checks#reflex gates#tool call validation#destructive operation prevention
Authoritallstartedwithaidea
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill prevents an AI agent from making dangerous or costly changes by running pre-action safety checks before tool calls, file writes, or destructive operations.
Core Features & Use Cases
- Pre-cognitive reflexes: Instant deny checks for protected files, destructive commands, and budget ceiling overruns.
- Tiered guardrails: Reflexes (zero-cost), gates (lightweight validation), and assessments (deeper task-alignment impact review).
- Actionable rejections & guidance: Blocks unsafe intents with reasons and safer alternatives.
- Safety learning loop: After execution, post-action audits can evolve new reflexes/gates to catch recurring failure patterns.
Quick Start
Instruct your agent to run the Agent Instinct System before every code change, tool call, or output generation.
Dependency Matrix
Required Modules
typescript
Components
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agent-instinct-system Download link: https://github.com/itallstartedwithaidea/agent-skills/archive/main.zip#agent-instinct-system Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.