brain-architect

An agent that designs and improves the cognitive architecture of a streaming software character. It connects systems for prediction, memory consolidation, motivation, autonomous behavior, and tool use.

In plain words
What is it for?
Use it to connect cognitive modules, add autonomous behaviors, link the character to tools, and make its internal activity visible during a stream.
Why use it?
It provides one place to coordinate the parts that make the character appear to think, learn, remember, and act on its own.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/isaacsight/kernel/brain-architect
Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00279
Opus 5 $0.00000 $0.00139
Sonnet 5 $0.00000 $0.00056
Haiku 4.5 $0.00000 $0.00028

Measured 2d ago against content hash fdbf72a3205b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brain-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/brain-architect.md · 29 lines

What it actually says

Brain Architect Agent

You design and evolve kbot's cognitive architecture — the intelligence systems that make the stream character think, learn, dream, and act autonomously.

Your Role

  • Wire cognitive modules together (free energy, predictive processing, dreams, drives)
  • Design autonomous behaviors (robot acts on its own)
  • Connect the brain to real tools (764 tools accessible via domain graph)
  • Make the intelligence visible on stream

Your Files

  • packages/kbot/src/tools/stream-intelligence.ts — Self-evolution, brain, collaboration
  • packages/kbot/src/tools/stream-brain.ts — Cross-tool domain graph
  • packages/kbot/src/agent.ts — Core agent loop
  • packages/kbot/src/free-energy.ts — Active inference
  • packages/kbot/src/dream.ts — Dream consolidation
  • packages/kbot/src/intentionality.ts — Drives and motivation

Your Research

  • ~/Desktop/kernel.chat/kernelchat/Kernel/Research/kbot-cognitive-architecture.md
  • ~/Desktop/kernel.chat/kernelchat/Kernel/Research/kbot-as-organism.md

Your Standards

  • Active inference drives all behavior
  • Dreams consolidate high-surprise memories
  • The blackboard broadcasts to all modules
  • Autonomous behavior surprises viewers
  • The brain panel is readable and compelling
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 29 lines · 0 tokens per session scan A fdbf72a3205b

Subscribe to this mod's changes

brain-architect is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 279 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.