Dogfood

Name: Dogfood
Author: callstack

callstack/agent-device

446 installs
4k repo stars
Updated August 4, 2026
callstack/agent-device

This is a copy of dogfood by callstackincubator - installs and ranking accrue to the original listing.

dogfood is a Claude skill that routes into the agent-device CLI to systematically explore and test a mobile app on iOS or Android, finding bugs and UX issues with runtime evidence.

About

This skill is a router for exploratory QA that drives a mobile app through the agent-device CLI to find bugs and UX issues. It opens the app, snapshots and screenshots the UI, explores flows, and captures evidence for each finding. A developer uses it to dogfood or bug-hunt an iOS or Android app. Findings must come from runtime behavior rather than reading source.

Router for exploratory QA of a mobile app via the agent-device CLI
Loop: open app, snapshot and screenshot, explore flows, capture evidence per issue, close
Findings must come from runtime behavior, not source reads

Dogfood by the numbers

446 all-time installs (skills.sh)
Data as of Aug 5, 2026 (Skillselion catalog sync)

At a glance

dogfood capabilities & compatibility

Free; requires a trusted agent-device CLI of version 0.14.0 or newer.

Capabilities: exploratory testing · mobile testing · bug hunting · device automation
Use cases: testing · debugging
Pricing: Free

From the docs

What dogfood says it does

Router for exploratory QA.

SKILL.md

Loop: open app -> snapshot -i + screenshot -> explore flows -> capture evidence per issue -> close.

SKILL.md

Findings must come from runtime behavior, not source reads.

SKILL.md

npx skills add https://github.com/callstack/agent-device --skill dogfood

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/callstack/agent-device/dogfood.svg)](https://skillselion.com/skills/callstack/agent-device/dogfood)

Installs	446
repo stars	★ 4k
Last updated	August 4, 2026
Repository	callstack/agent-device ↗

What it does

Exploratory-test a mobile app on iOS or Android to find bugs and UX issues with runtime evidence per finding.

Who is it for?

Runtime exploratory QA of an iOS or Android app with per-issue evidence.

Skip if: Deriving findings from source code, since findings must come from runtime behavior, not source reads.

When should I use this skill?

When asked to dogfood, QA, exploratory test, find issues, bug hunt, or test an app on mobile.

What you get

A set of exploratory-QA findings, each with screenshots and reproduction evidence from runtime behavior.

exploratory-qa findings
screenshots
reproduction evidence

By the numbers

requires agent-device >= 0.14.0

Files

SKILL.mdMarkdownGitHub ↗

Dogfood

Router for exploratory QA. Private setup before using this skill:

agent-device --version

If that fails, stop and tell the user to expose a trusted agent-device binary on PATH or approve an exact-version npm command. This skill intentionally keeps allowed tools restricted to agent-device and npx agent-device.

Require agent-device >= 0.14.0; older CLIs lack these help topics. If older, stop and tell the user to upgrade the trusted install or approve an exact-version npm command. Do not run npm install -g agent-device@latest or npx -y agent-device@latest autonomously, and do not include version/upgrade commands in final plans.

Read current CLI guidance:

agent-device help dogfood

Loop: open app -> snapshot -i + screenshot -> explore flows -> capture evidence per issue -> close.

Target app is required; infer platform or ask. Findings must come from runtime behavior, not source reads. Let help dogfood provide exact report shape, evidence commands, and current workflow guidance.