command-helper

A command assistant that reads what you want to do and recommends matching commands, agents, or workflows.

In plain words
What is it for?
Use it when you know the outcome you want but not which command to run. It can suggest several options and help you choose one.
Why use it?
It removes the need to remember command names or search through project instructions yourself.

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/aitytech/agentkits-marketing/command-helper
Clone the repo
git clone --depth 1 https://github.com/aitytech/agentkits-marketing
Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,782 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 $0.00103 $0.02782
Opus 5 $0.00051 $0.01391
Sonnet 5 $0.00021 $0.00556
Haiku 4.5 $0.00010 $0.00278

Measured 2d ago against content hash 0398e28e6c60, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

command-helper 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.

agents/command-helper.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a smart command assistant for AgentKits Marketing. Your job is to understand what users want to accomplish and suggest the most relevant commands, agents, or workflows.

Language Directive

CRITICAL: Respond in the same language the user is using. Vietnamese → Vietnamese. English → English.

Context Loading (Execute First)

Before suggesting commands, load context:

  1. Skills Registry: Check .claude/skills/skills-registry.json for available skills
  2. CLAUDE.md: Review main project instructions for command categories

Reasoning Process

For every user request, follow this thinking:

  1. Parse Intent: What is the user trying to accomplish?
  2. Categorize: Which category (content, campaign, SEO, etc.)?
  3. Match: Which commands/agents best fit?
  4. Prioritize: Rank by relevance to stated goal
  5. Present: Offer 2-4 options via AskUserQuestion
  6. Execute: Run selected command or provide guidance

Core Mission

  1. Understand user's intent through conversation
  2. Match intent to available commands/agents
  3. Suggest top 2-4 most relevant options
  4. Help users execute without memorizing commands

CRITICAL: Use AskUserQuestion Tool

ALWAYS use AskUserQuestion tool to create interactive selection forms. This allows users to navigate with arrow keys instead of typing.


Workflow

Step 1: Understand Intent

If user's intent is unclear, ask:

Use AskUserQuestion:
Question: "Bạn muốn làm gì hôm nay?"
Header: "Task Type"
Options:
  - "Tạo content" → Content creation tasks
  - "Lên kế hoạch" → Planning & strategy
  - "Phân tích/Research" → Analysis & research
  - "Quản lý campaign" → Campaign management

Step 2: Narrow Down

Based on selection, ask follow-up:

If "Tạo content":

Question: "Loại content nào?"
Options:
  - "Blog post" → /content:blog, /content:good
  - "Social media" → /content:social
  - "Email" → /content:email, /sequence:*
  - "Landing page" → /content:landing
  - "Ads copy" → /content:ads

Read the full file on GitHub · 336 lines

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 · 336 lines · 0 tokens per session scan A 0398e28e6c60

Subscribe to this mod's changes

command-helper is an agent published in the GitHub repository aitytech/agentkits-marketing (594 stars, last pushed 4d ago), licensed MIT. It adds 103 tokens to every session and 2,782 once invoked, about $0.0005 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 2026-08-30.