callstack/agent-device is a toolset that lets coding agents inspect, control, debug, and verify running apps on mobile, desktop, web, and TV platforms. Developers use its CLI, MCP server, or Node.js API to test application changes on simulators, emulators, physical devices, and remote device clouds. The catalogue entries provide agent integrations and instructions for using it.
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.
npx skills add callstack/agent-device --skill dogfoodgit clone --depth 1 https://github.com/callstack/agent-deviceWrote 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.
[](https://agentmods.dev/skills/callstack/agent-device/dogfood)<a href="https://agentmods.dev/skills/callstack/agent-device/dogfood"><img src="https://agentmods.dev/badge/skills/callstack/agent-device/dogfood/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.
<a href="https://agentmods.dev/skills/callstack/agent-device/dogfood"><img src="https://agentmods.dev/badge/skills/callstack/agent-device/dogfood.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 4 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 15 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 17 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.00306 |
| Opus 5.5 | $0.00022 | $0.00122 |
| Sonnet 5.5 | $0.00011 | $0.00061 |
| Haiku 4.5 | $0.00006 | $0.00031 |
Grade A, and why
dogfood 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 1mo 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.
What it actually says
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.
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.
- 1mo ago First seen · 28 lines · 55 tokens per session scan A e7f1793c8d48
dogfood is a skill published in the GitHub repository callstack/agent-device (5,034 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 306 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 2026-08-30.
Other skills, from other repositories
rn-testing
This skill should be used when the user asks to "write a Maestro test", "create E2E flows", "add testIDs", "run UI tests", "run E2E tests", "verify a feature works", "test my screen", "set up maestro-runner", "mock network requests", "inspect store state", "write test assertions", or needs guidance on test timing…
capturing-proof
This skill should be used when the user asks to "capture proof", "record a demo of this feature", "make a video showing it works", "record the flow for the PR", "generate a PR body", "capture screenshots for the PR", "proof-capture", or when a verified feature needs PR-ready proof artifacts (video + numbered…
run-action
Explicit Codex workflow: Execute a learned Maestro flow ("action") by name with optional -e KEY=VALUE parameters. Looks the flow up via packages/rn-dev-agent-core/dist/learned-actions.js (same inventory as $rn-dev-agent:list-learned-actions), then replays it via cdprunaction — auto-repair-aware orchestration with…
build-and-test
Explicit Codex workflow: Build the Expo/React Native app (local or EAS), install it, start Metro, then test a requested feature end-to-end.
test-feature
Explicit Codex workflow: Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
qa-pr
Explicit Codex workflow: Device-test a GitHub pull request on iOS simulator, Android emulator, and/or physical device. Installs the PR head via rn-dev-agent and reports pass/fail with repro steps and screenshots.