a vendor-neutral runtime protocol for autonomous AI coding agents persistent memory, execution loops, verification, events, and handoffs inside your repo.
Command Claude Code
Planning Mode — scaffold a target project's l00prite/ folder (CLAUDE.md blueprint, AGENTS.md, .l00prite memory, universal loop prompts), root pointer files, vendor adapters, and a skeleton repo from a project idea. Stops after scaffolding; --execute hands off to Execution Mode only through execute-loop's confirmed…
Command Claude Code
Enter Execution Mode for the current l00prite-managed project — autonomous run behind a pre-flight confirmation gate. Requires explicit in-session confirmation before any iteration.
Command Codex
You are processing one pending l00prite event. Events are protocol objects, not vendor-specific automation commands.
Command Codex
Prepare a cross-agent handoff for a l00prite-managed project.
Command Codex
You are performing a l00prite heartbeat check. Do not implement features during this check.
Command Codex
You are responding to one review-related l00prite event. Treat .l00prite/ as the shared source of truth across agents.
Command Codex
You are resuming a l00prite-managed project. Treat .l00prite/ as the shared source of truth across Claude, Codex, GPT, Gemini, and future agents.