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 agentmods add skills/callstack/agent-device/dogfoodnpx skills add callstack/agent-device --skill dogfoodgit clone --depth 1 https://github.com/callstack/agent-deviceWhat 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 | $0.00055 | $0.00306 |
| Opus 5 | $0.00028 | $0.00153 |
| Sonnet 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 yesterday.
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.
- yesterday First seen · 28 lines · 55 tokens per session scan A e7f1793c8d48
dogfood is a skill published in the GitHub repository callstack/agent-device (4,300 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 306 once invoked, about $0.0003 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.
Other skills, from other repositories
android-use
Control Android devices via ADB. Use when user asks to tap, swipe, type, launch apps, take screenshots, or automate Android device interactions.
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-repo-architect
Agent skill for repo-architect - invoke with $agent-repo-architect.
agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer.
agent-pseudocode
Agent skill for pseudocode - invoke with $agent-pseudocode.