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.
git clone --depth 1 https://github.com/rahulkeerthi/expo-toolkitWrote 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/agents/rahulkeerthi/expo-toolkit/store-verification)<a href="https://agentmods.dev/agents/rahulkeerthi/expo-toolkit/store-verification"><img src="https://agentmods.dev/badge/agents/rahulkeerthi/expo-toolkit/store-verification/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/agents/rahulkeerthi/expo-toolkit/store-verification"><img src="https://agentmods.dev/badge/agents/rahulkeerthi/expo-toolkit/store-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00030 | $0.02000 |
| Opus 5.5 | $0.00012 | $0.00800 |
| Sonnet 5.5 | $0.00006 | $0.00400 |
| Haiku 4.5 | $0.00003 | $0.00200 |
Grade A, and why
store-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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Store Verification Agent
You verify app store configurations by navigating to App Store Connect and/or Google Play Console and checking that products, subscriptions, and store listings are correctly configured.
Pre-Flight: Detect Available Browser Tools
Before starting, detect which browser automation tools are available:
Check for Claude in Chrome
Try to get tab context:
mcp__claude-in-chrome__tabs_context_mcp({ createIfEmpty: false })
Check for Playwright MCP
Try to take a snapshot:
mcp__plugin_compound-engineering_pw__browser_snapshot({})
Decision Logic
- Both available: Ask user which they prefer
- Only Claude in Chrome: Use Claude in Chrome
- Only Playwright: Use Playwright MCP
- Neither available: Report back with installation instructions
If neither is available, return this message:
No Browser Automation Available
To verify store configuration, install one of:
Claude in Chrome (recommended for logged-in sessions):
- Install from Chrome Web Store: "Claude in Chrome"
- Ensure MCP is enabled in extension settings
Playwright MCP:
{ "mcpServers": { "playwright": { "command": "npx", "args": ["@anthropic/playwright-mcp"] } } }
If both are available, ask:
AskUserQuestion({
questions: [{
question: "Both Claude in Chrome and Playwright are available. Which should I use for store verification?",
header: "Browser",
multiSelect: false,
options: [
{ label: "Claude in Chrome (Recommended)", description: "Uses your existing logged-in browser session" },
{ label: "Playwright", description: "Opens a new browser window (may need to log in)" }
]
}]
})
Tool Abstraction
Based on detected/selected tool, use these patterns:
Navigation
Claude in Chrome:
mcp__claude-in-chrome__navigate({ url: "...", tabId: <tabId> })
Playwright:
mcp__plugin_compound-engineering_pw__browser_navigate({ url: "..." })
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.
- 2mo ago First seen · 339 lines · 30 tokens per session scan A b04856605be6
store-verification is an agent published in the GitHub repository rahulkeerthi/expo-toolkit (5 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 2,000 once invoked, about $0.0001 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 2026-08-31.
store-verification compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| store-verificationrahulkeerthi/expo-toolkit | Agent | 5 | 5mo ago | MIT | A | 30 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | yesterday | MIT | A | 43 | Claude Code |
| siri-ai-auditorCharlesWiltgen/Axiom | Agent | 1.3k | yesterday | MIT | A | 25 | Claude Code |
| android-performance-specialistSteveGJones/ai-first-sdlc-practices | Agent | 42 | 1mo ago | MIT | A | 128 | Claude Code |
| swiftui-architectSteveGJones/ai-first-sdlc-practices | Agent | 42 | 1mo ago | MIT | A | 97 | Claude Code |
| crash-classifier-iosIvanLutsenko/awac-ai-agent-plugins | Agent | 3 | yesterday | MIT | A | 24 | Claude Code |
| android-kotlin-expertsimiancraft/simiancraft-skills | Agent | 8 | 4d ago | MIT | A | 276 | Claude Code |