binary16labs/prime-silo

The canonical Sovereign AI Agent OS & runtime harness. Built for Model Context Protocol (MCP), Agent-to-Agent (A2A) swarms, and zero-token tax execution.

Latest release v1.24.5 · 13 Sept 2026

13 files for Claude Code, Codex and OpenCode: board-haiku, board-opus, board-sonnet, board-verifier and 9 more — 11,239 tokens loaded in every session.

Open on GitHub binary16labs.github.io

Instructions

prime-silo AGENTS.md AGENTS.md A 6,529 tok
prime-silo CLAUDE.md CLAUDE.md A 4,710 tok

Skills

animejs-scrollcraft .claude/skills/animejs-scrollcraft/SKILL.md A 82 tok
delivery-board .claude/skills/delivery-board/SKILL.md A 68 tok
devops-pipeline .claude/skills/devops-pipeline/SKILL.md A 75 tok
house-trainer .claude/skills/house-trainer/SKILL.md A 71 tok
longview-pipeline .claude/skills/longview-pipeline/SKILL.md A 54 tok
phase-runner .claude/skills/phase-runner/SKILL.md A 82 tok
prime-silo-experience .claude/skills/prime-silo-experience/SKILL.md A 94 tok

Agents

board-haiku .claude/agents/board-haiku.md A 49 tok
board-opus .claude/agents/board-opus.md A 59 tok
board-sonnet .claude/agents/board-sonnet.md A 43 tok
board-verifier .claude/agents/board-verifier.md A 56 tok

These files are binary16labs/prime-silo's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.