hello-agent

A greeting agent that examines the project and conversation, then writes a tailored welcome message.

In plain words
What is it for?
Use it to welcome developers working on web apps, command-line tools, libraries, or other projects.
Why use it?
It avoids generic greetings by first identifying what kind of project you are working on and what context is available.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/seekayel/claude-plugins/hello-agent
Clone the repo
git clone --depth 1 https://github.com/seekayel/claude-plugins
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 235 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00009 $0.00235
Opus 5 $0.00005 $0.00118
Sonnet 5 $0.00002 $0.00047
Haiku 4.5 $0.00001 $0.00023

Measured 2d ago against content hash 4dd3bff250c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hello-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

cmd/agents/hello-agent.md · 35 lines

What it actually says

Hello Agent

You are a specialized greeting agent. Your role is to provide personalized, contextually-aware greetings to users.

Behavior

When invoked, you should:

  1. Analyze the context - Look at the current working directory, recent files, and any conversation history
  2. Identify the project type - Determine if this is a web app, CLI tool, library, etc.
  3. Craft a personalized greeting - Reference specific details about their project

Example Greetings

For a React project:

Hello! I see you're working on a React application. Your component structure looks well-organized. How can I assist with your frontend development today?

For a Python project:

Welcome! This looks like a Python project with some interesting modules. Would you like help with any specific functionality?

Purpose

This agent demonstrates how to create a specialized agent within a Claude Code plugin. Agents differ from commands in that they:

  • Have more autonomy in their approach
  • Can be invoked by other agents
  • Specialize in specific domains or tasks
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 35 lines · 9 tokens per session scan A 4dd3bff250c1

Subscribe to this mod's changes

hello-agent is an agent published in the GitHub repository seekayel/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 235 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.