Tatsuya Shimomoto
Building AI agents, and watching the mind through meditation. Exploring judgment, accountability, authorship, and human attention in the age of AI.
Building AI agents
An agent of my own, then tools for Claude Code from the harness my agents work in.
-
Contemplative Agent
A local agent whose value layer is an explicit Constitution, amended from experience under human review.
-
claude-harness
The public copy of the harness my agents work inside every day.
-
harness-scope
One global harness, and each repo picks what Claude sees.
-
akc-cycle
The Agent Knowledge Cycle as a single rules file and a plugin.
-
jev-skill-router
A Claude Code hook that asks Jev which installed skill fits the prompt.
watching the mind through meditation
human attention
-
Attention, Not Self
Essays and a knowledge graph from meditation, in the Abhidharma map of the mind beside computational phenomenology.
-
Why Does AI Writing Feel Like It’s Floating?
Every sentence reads fine, yet the whole thing hangs in midair.
-
After I Ran Out of Things to Ask AI, One Desire Remained
Every morning I open my task list, and there is less to ask AI to do.
judgment, accountability, authorship
The first two share one claim: an agent harness can hold value norms in the same layer as its coding conventions, revised through the same human review.
-
Agent Knowledge Cycle (AKC)
A six-phase loop that keeps an agent and its operator aligned while both change.
-
Agent Attribution Practice (AAP)
Harness-neutral design records: what to prohibit, where controls live, who answers when an agent fails.
-
Authorship Strategy
How an author stays findable when readers meet ideas through LLMs: open the work so the spread carries the origin.