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 agents/callstack/agent-device/device-verificationgit 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 | $0.00000 | $0.00760 |
| Opus 5 | $0.00000 | $0.00380 |
| Sonnet 5 | $0.00000 | $0.00152 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
device-verification 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manual Device Verification
Read this before running agent-device by hand against a simulator, emulator, or physical device.
Before the run: defeat staleness
Dev-loop staleness has three layers, and each produces a convincing false negative.
- After changing runtime code reached through
bin/agent-device.mjsor the daemon:pnpm build, thenpnpm clean:daemon— the daemon does not self-reload. - Before any Android verification from source:
pnpm build,pnpm build:android,pnpm clean:daemon.build:androidrefreshes and verifies both bundled Android helper artifacts for the current package version. shutdowndeliberately HANDS OFF a healthy simulator runner. The adopted runner keeps serving the old Swift binary until you kill its process or the source fingerprint changes, so "my change did nothing" measured against an adopted runner is a classic false negative. If Swift runner code changed, runpnpm build:xcuitest.
Prove the path under test was actually active
- Android: capture
snapshot -i --jsonand requireandroidSnapshot.backendto beandroid-helperwithhelperVersionequal topackage.json's version. A stock UIAutomator fallback is not valid verification unless the fallback itself is the behavior under test. - For repo-owned
Agent Device Testerwork,examples/test-app/README.mdis the source of truth for simulator, physical-device, Metro/dev-client, and app-surface steps. An already-installedcom.callstack.agentdevicelabis not sufficient — the README's Metro/dev-build andsnapshot -ichecks must prove the expected app surface is running. - For Android RN/Expo/dev-client apps on any local Metro port,
adb reverse tcp:<port> tcp:<port>is harmless and should be run before opening the app or URL.
Session hygiene
Every manually opened session is a resource that must be closed — including exploratory sessions and failed verification attempts.
- Every
agent-device openneeds a matchingclosewith the same--session,--platform,--udid, and--state-dirbefore the agent finishes. - Use a purpose-specific session name for experiments, and an isolated
--state-dirunder/private/tmpwhen you need cleanup isolation beyond the current worktree's default daemon. - Track opened sessions in working notes; close each one before the final response.
- If
closeis blocked or ownership looks stuck, inspect it withagent-device device status --stale(daemonless), stop the owning daemon withagent-device daemon stop --state-dir <dir>(add--cleanto remove retained runners), and release provably dead owners withagent-device device release --stale. Do not hunt PIDs withps/kill. - If cleanup cannot be completed, report the remaining session name, state dir, and the
device status --staleoutput as a blocker.
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 Changed · +2 lines 9f316d47692e
- 2d ago First seen · 54 lines · 0 tokens per session scan A 1a233de30441
device-verification is an agent published in the GitHub repository callstack/agent-device (4,300 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 760 tokens. 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 agents, from other repositories
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
backend-api-security-backend-security-coder
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
agent-orchestration-context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…
basic-agents
A basic agent uses a predefined strategy with a simple execution flow that works for most common use cases. It accepts a string input (a question, request, or task description) and sends this input to the configured LLM. The LLM may decide to call provided tools. The agent will execute the tools and send the results…
explainer
Code explanation and architecture walkthroughs. Helps developers understand complex code and systems.
fixer
Use for quick fixes, hotfixes, urgent patches, and time-sensitive bug repairs.