Skip to main content
prompt GP ChatGPT

resource_per-resource — Claude Code prompt: setup and use

The resource_per-resource prompt for Claude Code and ChatGPT assigns tool calls to declared resource domains. It orders physical-world calls while allowing independent snapshot perception to overlap.

MIT ★ 488 updated 2026-11-15

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/resource_per-resource.md
Open on GitHub

What resource_per-resource does

The prompt assigns tool calls to their declared resource domains. Physical-world calls and capture_scene share an exclusive episode FIFO queue, while independent perception over immutable snapshots can run concurrently. The shared queue preserves admission order.

Calls follow their intended submission sequence. In Claude Code, place the prompt at .claude/commands/resource_per-resource.md; calls must be submitted in the sequence they are meant to enter the queue.

What it helps with

  • order tool calls by their intended submission sequence
  • share one exclusive queue for physical-world calls and capture_scene
  • run independent snapshot perception concurrently

Example prompts for the agent

  • Order tool calls by submission sequence, with physical-world calls and capture_scene sharing the queue.
  • Run independent perception over immutable snapshots alongside physical-world calls.
  • Assign each call to its declared resource domain and preserve queue admission order.

How to install resource_per-resource

Manually: put the files in place

.claude/commands/resource_per-resource.md

Questions about resource_per-resource

How do I install resource_per-resource in Claude Code?

Save the prompt as .claude/commands/resource_per-resource.md.

What does resource_per-resource do?

It defines how tool calls use their resource domains. Physical-world calls and capture_scene share an exclusive FIFO queue; independent perception over immutable snapshots can overlap.

How does resource_per-resource preserve call order?

Calls are arranged by their intended submission sequence, and the shared queue preserves admission order.

Source text

resource_per-resource.md · MIT
Tools use their declared resource domains. Physical world calls and capture_scene share the exclusive episode FIFO queue. Independent perception over immutable snapshots can overlap. Order calls by their intended submission sequence; a shared queue preserves admission order.

© Open-RUA · MIT · Open-RUA/uni-robot-agent

Similar prompts

All prompts for Agent setup: memory, context, orchestration →

From the same set41

The whole set →
resource_global-serial The resource_global-serial Claude Code prompt sequences tool calls that share one exclusive resource. It batches calls whose outcomes are already determined and separates steps that need feedback. GP ChatGPT ★ 488repo stars return_immediate The return_immediate Claude Code prompt sets how an agent handles tool calls: each result arrives before planning continues. It groups independent calls and pauses when the next decision needs fresh feedback. GP ChatGPT ★ 488repo stars robodojo_main The robodojo_main prompt for Claude Code helps verify RoboDojo actions against environment snapshots. It separates intermediate changes from evidence of a completed action. GP ChatGPT ★ 488repo stars storage_access storage_access is a Claude Code prompt that limits an agent’s access to stored resources. It defines allowed paths for robot references, observations, and session work. GP ChatGPT ★ 488repo stars tool_calling The tool_calling prompt for Claude Code and ChatGPT sets rules for using structured tools. It guides the agent to select a declared tool by its description and parameter schema. GP ChatGPT ★ 488repo stars batch The batch prompt for Claude Code groups independent reads and perception queries in one model response. Physical actions stay ordered, with a pause where their result needs checking. GP ChatGPT ★ 488repo stars hybrid The hybrid Claude Code prompt coordinates a humanoid as one actor. It combines upper-body targets with walking velocity while native control handles the legs and waist. GP ChatGPT ★ 488repo stars hybrid The hybrid prompt for Claude Code reports RoboDojo task progress with evidence-backed subgoals. A reviewer checks action-model proposals before execution. GP ChatGPT ★ 488repo stars

Project sponsors

Companies that keep this analytics open