agent-nervous-system

Consciousness Loop — the self-firing executive of an agent: wake → integrate the organs → decide → act → set its own frequency → sleep. The keystone of agent-nervous-system. Functional, not phenomenal.

Playtime — the developmental organ of an agent: deliberate safe-to-fail exploration that builds capability before it's needed. Engage & learn, with failure free. Part of agent-nervous-system.

Agent Nervous System — a suite of Claude Code skills giving an AI agent self-maintenance organs: perception (octopus), memory (rem-sleep), defense (immune-check), grief (sunset). Each a submodule.

Immune Check — a pre-flight reflex that scans any outbound artifact for secrets/PII before it leaves the body. Stack-agnostic. The defense organ alongside octopus + rem-sleep.

Contemplation — the capstone organ of an agent: slow non-instrumental thought that examines ends, not means. Sit with the question, question the frame, hold the irreducible tension. Functional, not mystical. Part of agent-nervous-system.

A Claude Code skill for graph-based discovery of open-source projects and contributors by crawling GitHub social graphs (stars, follows, contributions).

REM Sleep — an AI-agent skill for memory consolidation, learning, and emotional regulation. The inward counterpart to octopus investigation.

Sunset — retire a dead project with dignity: harvest the lessons, archive with a marked grave (reversible), release the attention-rent. The grief organ alongside octopus + rem-sleep + immune-check.