DogfoodSAFE
Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
Overview
Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
3ccae34ce0e0OBSERVED · 2026-10-21What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: dogfood description: Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile. allowed-tools: Bash(agent-device:*), Bash(npx agent-device:*) --- # Dogfood Router for exploratory QA. Private setup before using this skill: ```bash 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: ```bash 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.
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
3ccae34ce0e0full audit observations/trust-audit/skill/callstack__dogfood.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-21 | 3ccae34ce0e0 | SAFE | B | 89 | first audit |
Questions
What does the dogfood — callstack/agent-device skill do?
Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
Is dogfood — callstack/agent-device safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can dogfood — callstack/agent-device access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (3ccae34ce0e0), read on 2026-10-21. The repository is watched, and a new audit runs when it changes — this is the first audit.
Add this badge to your README
Shows this page's audit result and links back to it. It updates when the audit does.
[](https://modelsatlas.com/skills/callstack/dogfood/)
Not your listing, or something out of date? Claim or update your listing.