arc-observing

Name: arc-observing
Availability: InStock
Author: Gregory

Manage detected AI behavioral instincts with confidence scores and daemon controls.

6|Updated Feb 8, 2026

Search Tags:#pattern detection #tool usage #agent management #daemon #instincts #ai behavior

Ready to run

npx skills add https://github.com/GregoryHo/arcforge --skill arc-observing

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: arc-observing
Source: https://github.com/GregoryHo/arcforge/tree/main/skills/arc-observing
Command: npx skills add https://github.com/GregoryHo/arcforge --skill arc-observing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you understand and manage the behavioral patterns of AI agents by automatically detecting recurring actions and providing tools to confirm or contradict these detected patterns.

Core Features & Use Cases

Instinct Detection: Automatically identifies behavioral patterns (instincts) from tool usage.
Instinct Management: Allows users to confirm or contradict detected patterns, influencing their confidence scores.
Daemon Control: Provides commands to start, stop, and check the status of the background observer daemon.
Use Case: If an AI agent consistently uses a specific sequence of tools before editing a file, this skill can detect that pattern, present it to you as an "instinct," and allow you to confirm it, reinforcing that behavior for future sessions.

Quick Start

View the status of all detected behavioral instincts for the current project.

Frequently Asked Questions about arc-observing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I detect and manage recurring AI agent behavior patterns?▼

You can detect and manage recurring AI agent behavior patterns by running a background observer daemon that captures tool calls, analyzes them for recurring sequences, and saves them as markdown instincts. You then confirm or contradict these instincts to influence future sessions.

How does AI instinct detection work for tool usage?▼

AI instinct detection works by using a background daemon to capture tool calls and an LLM to analyze the captured sequences. When a behavioral pattern is identified, it is saved as a markdown file with a confidence score that you can manually confirm or contradict.

Can I manage project-specific and global AI instincts separately?▼

Yes, you can manage project-specific and global AI instincts separately. The skill supports both scopes, allowing you to apply behavioral patterns globally or restrict them to the current project's context.

How do I control the background daemon observing AI tool calls?▼

You control the background daemon observing AI tool calls using specific commands to start, stop, and check its status. This daemon runs continuously to capture tool usage data for pattern analysis.

What happens to unconfirmed AI behavioral instincts over time?▼

Unconfirmed AI behavioral instincts experience confidence decay over time. The skill includes a confidence decay mechanism that reduces the influence of older, unverified patterns, and an archiving system to manage them.

How do I reinforce or correct detected AI tool usage sequences?▼

You reinforce or correct detected AI tool usage sequences by confirming or contradicting the instincts generated by the observer. Confirming a pattern increases its confidence score and auto-loading behavior, while contradicting it prevents future automatic application.