Skip to main content
prompt GP ChatGPT

resource_global-serial — Claude Code prompt: calls in order

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.

MIT ★ 488 updated 2026-11-15

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

What resource_global-serial does

The prompt makes tools sharing one resource take turns. Calls run one at a time, in the order they enter the queue. Calls with decisions already settled can be batched, reducing planning exchanges.

A step that depends on an intermediate result starts a separate batch. The agent needs that feedback before deciding what comes next. For Claude Code, place the prompt file at .claude/commands/resource_global-serial.md.

What it helps with

  • queue calls that share an exclusive resource
  • run tool calls one at a time in admission order
  • batch calls with decisions already settled
  • split steps that depend on intermediate feedback

Example prompts for the agent

  • Queue calls to shared tools and run them in the order received.
  • Batch calls whose outcomes are already decided, but split steps that need an intermediate result.
  • Run only one call to the shared resource at a time.

How to install resource_global-serial

Manually: put the files in place

.claude/commands/resource_global-serial.md

Questions about resource_global-serial

How do I install resource_global-serial in Claude Code?

Place the prompt file at .claude/commands/resource_global-serial.md.

What does resource_global-serial do?

It sets a sequence for tools that share one exclusive resource. Calls run one at a time; predetermined calls can be batched, while steps needing intermediate feedback stay separate.

How does resource_global-serial handle tool calls?

Calls follow their admission order and execute one at a time. Batching is for calls whose decisions are already determined.

Source text

resource_global-serial.md · MIT
All tools share one exclusive FIFO resource. Calls execute one at a time in admission order. Batch already-determined calls to reduce planning exchanges, but split at decisions requiring intermediate feedback.

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

Similar prompts

Prompts catalog →

From the same set41

The whole set →
resource_per-resource 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. 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