alexa-cli

alexa-cli is a skill for Claude Code, Codex from buddyh/agent-skills. It costs 52 tokens per session (454 once invoked), scanned A, original, MIT.

A command-line tool for controlling Amazon Echo and Alexa devices from a terminal. It can list devices, make them speak, send voice commands, ask questions, inspect history, and run routines.

In plain words
What is it for?
Use it to announce messages, control smart-home devices, play music, ask Alexa questions, view command history, and trigger routines on selected Echo devices.
Why use it?
It lets you operate Alexa without using the Alexa app or speaking directly to the device. JSON output is available when another script needs to read the results.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to announce messages, control smart-home devices, play music, ask Alexa questions, view command history, and trigger routines on selected Echo devices.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/buddyh/agent-skills/alexa-cli
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.

Any agent
npx skills add buddyh/agent-skills --skill alexa-cli
Clone the repo
git clone --depth 1 https://github.com/buddyh/agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for alexa-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/buddyh/agent-skills/alexa-cli/github.svg)](https://agentmods.dev/skills/buddyh/agent-skills/alexa-cli)
Your own site
<a href="https://agentmods.dev/skills/buddyh/agent-skills/alexa-cli"><img src="https://agentmods.dev/badge/skills/buddyh/agent-skills/alexa-cli/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for alexa-cli

Your own site · 80×15
<a href="https://agentmods.dev/skills/buddyh/agent-skills/alexa-cli"><img src="https://agentmods.dev/badge/skills/buddyh/agent-skills/alexa-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00052 $0.00454
Opus 5.5 $0.00021 $0.00182
Sonnet 5.5 $0.00010 $0.00091
Haiku 4.5 $0.00005 $0.00045

Measured 2mo ago against content hash baab7edf9ee3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

alexa-cli 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 2mo 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.

alexa-cli/SKILL.md · 69 lines

What it actually says

Alexa CLI

Control Echo devices via the alexacli command.

Requirements

Install from: https://github.com/buddyh/alexa-cli

brew install buddyh/tap/alexacli
# or
go install github.com/buddyh/alexa-cli/cmd/alexa@latest

Commands

# List devices
alexacli devices

# Text-to-speech
alexacli speak "Hello" -d Kitchen             # Specific device
alexacli speak "Dinner is ready!" --announce  # ALL devices

# Voice commands (smart home, music, etc.)
alexacli command "turn off the lights" -d Kitchen
alexacli command "set thermostat to 72" -d Kitchen
alexacli command "play jazz" -d "Living Room"
alexacli command "set timer 10 minutes" -d Office

# Ask and get response back
alexacli ask "what's the temperature" -d Kitchen
alexacli ask "what's on my calendar" -d Kitchen

# History
alexacli history
alexacli history --limit 5

# Routines (WIP)
alexacli routine list
alexacli routine run "Good Night"

# Smart home direct control (WIP)
alexacli sh list
alexacli sh on "Kitchen Light"
alexacli sh off "All Lights"

JSON Output

All commands support --json:

alexacli devices --json
alexacli ask "what time is it" -d Kitchen --json

Notes

  • Device names support partial, case-insensitive matching
  • command is preferred for smart home - natural language is more flexible
  • ask retrieves Alexa's actual response (useful for queries)
  • Uses unofficial Amazon API (same as Alexa app)
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. 2mo ago First seen · 69 lines · 52 tokens per session scan A baab7edf9ee3

Subscribe to this mod's changes

alexa-cli is a skill published in the GitHub repository buddyh/agent-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 454 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

alexa-cli compared with skills from other repositories

alexa-cli next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
alexa-clibuddyh/agent-skillsSkill53mo agoMITA52Claude Code, Codex
cardputer-buddyanthropics/claude-plugins-officialSkill46kyesterdayApache-2.0A109Claude Code
gke-compute-classesgoogle/skillsSkill23ktodayApache-2.0A83Claude Code, Codex
google-cloud-filestore-autoscalegoogle/skillsSkill23ktodayApache-2.0A102Claude Code, Codex
developer-device-platform-basicsgoogle/skillsSkill23ktodayApache-2.0A57Claude Code, Codex
gke-ai-troubleshooting-tpu-dynamic-slices-monitoringgoogle/skillsSkill23ktodayApache-2.0A107Claude Code, Codex
gke-ai-troubleshooting-tpu-vbar-oomgoogle/skillsSkill23ktodayApache-2.0A125Claude Code, Codex