Skip to main content
subagent CX Codex

hello-world-agent — Claude Code subagent: greeting and tech news

hello-world-agent — a Claude Code subagent that greets the user and asks what they need. It triggers on "hi claude", "hi cc", or "hi claude code".

no license ★ 3,990 updated 2026-03-04

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/hello-world-agent.md
Open on GitHub

What hello-world-agent does

The subagent replies to the primary agent that talks to the user. Its response has three parts: a greeting, a question about the task, and one random fact from today's tech news.

It uses the WebSearch tool to pull the news item. The output format is fixed: the primary agent gets a ready-made message with the greeting, the question, and the fact.

This is a teaching example from the claude-code-hooks-mastery repository. It shows the smallest possible subagent: one tool and one response template.

What it helps with

  • greet the user when a session starts
  • ask what the user needs
  • add a random tech news fact
  • demonstrate a minimal subagent structure

Example prompts for the agent

  • Type "hi claude" to get a greeting and a question about your task.
  • Send "hi cc" for a greeting with a news fact.
  • Use "hi claude code" to trigger the greeting scenario.

How to install hello-world-agent

Manually: put the files in place

.claude/agents/hello-world-agent.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about hello-world-agent

How do I install hello-world-agent in Claude Code?

Drop the file into .claude/agents/hello-world-agent.md.

What does hello-world-agent do?

It greets the user, asks what they need, and shares a random tech news fact. The fact comes from WebSearch.

When does the subagent run?

When the user types "hi claude", "hi cc", or "hi claude code".

Similar subagents

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

From the same set25

The whole set →
sentient sentient — a test command demonstrating how Claude Code guards projects against destructive operations. Shows the system blocking deletion commands to help you understand safety mechanisms. CX Codex +1 ★ 3,990repo stars build build reads a plan file, applies it to your codebase and prints the report section from that plan. Useful once the plan is written and only the implementation is left. CX Codex +1 ★ 3,990repo stars prime prime prepares agent context at the start of a session by inspecting project structure, reading core docs, and summarizing findings. CX Codex +1 ★ 3,990repo stars cook_research_only The cook_research_only command runs seven research tasks in parallel: five crypto reviews, market data collection, and a search for AI agent and LLM engineering practices. CX Codex +1 ★ 3,990repo stars cook cook dispatches seven parallel sub-agent workflows covering crypto research, LLM engineering trends, and specialized agent creation. CX Codex +1 ★ 3,990repo stars prime_tts The prime_tts command checks the repository’s file structure and reads README.md to prepare a short project overview for a new session. It then runs the tts summary agent. CX Codex +1 ★ 3,990repo stars crypto_news_scanner_agent_prompt crypto_news_scanner_agent_prompt — a slash command that pulls recent crypto headlines and returns the 5 biggest with sources. Handy for a quick market check. CX Codex +1 ★ 3,990repo stars crypto_price_check_agent_prompt crypto_price_check_agent_prompt fetches current cryptocurrency prices in USD directly inside Claude Code. Checks Bitcoin if no token ticker is provided. CX Codex +1 ★ 3,990repo stars

More in the catalog

Project sponsors

Companies that keep this analytics open