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/commands/rahulkeerthi/expo-toolkit/init)<a href="https://agentmods.dev/commands/rahulkeerthi/expo-toolkit/init"><img src="https://agentmods.dev/badge/commands/rahulkeerthi/expo-toolkit/init/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/commands/rahulkeerthi/expo-toolkit/init"><img src="https://agentmods.dev/badge/commands/rahulkeerthi/expo-toolkit/init.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 | $0.00020 | $0.03203 |
| Opus 5.5 | $0.00008 | $0.01281 |
| Sonnet 5.5 | $0.00004 | $0.00641 |
| Haiku 4.5 | $0.00002 | $0.00320 |
Grade A, and why
init 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 — 576 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expo Project Initialisation Wizard
Guide the user through setting up a new or existing Expo project with proper EAS configuration, environment-specific bundle IDs, and best practices.
Workflow Overview
- Detect project state - New project or existing?
- Gather app information - Name, bundle ID base, etc.
- Configure EAS - Initialise and set up build profiles
- Set up environments - Dev, preview, production bundle IDs
- Configure push notifications - If needed
- Customise project - README, CLAUDE.md updates
- Summary and next steps
Project Detection
First, check the current project state:
# Check if in an Expo project
ls app.json app.config.js package.json 2>/dev/null | head -5
# Check if EAS is already configured
ls eas.json 2>/dev/null && echo "EAS configured" || echo "EAS not configured"
# Check for existing Expo installation
grep -q "expo" package.json 2>/dev/null && echo "Expo found" || echo "Expo not found"
Interactive Setup
Step 1: Project Status
AskUserQuestion({
questions: [
{
question: "What's the current state of your project?",
header: "Project",
options: [
{
label: "New Expo project",
description: "Just created with 'npx create-expo-app' or similar",
},
{
label: "Existing Expo project",
description: "Already have an Expo app, adding EAS",
},
{
label: "Converting React Native project",
description: "Existing RN app, adding Expo support",
},
],
multiSelect: false,
},
],
});
Step 2: App Information
AskUserQuestion({
questions: [
{
question: "What's your app name? (used for display)",
header: "App Name",
// Free text input via "Other"
options: [
{
label: "Use existing name",
description: "Keep the current app name from config",
},
],
multiSelect: false,
},
{
question: "What's your bundle ID base? (e.g., com.yourcompany.yourapp)",
header: "Bundle ID",
options: [
{
label: "Use existing bundle ID",
description: "Keep current bundle identifier",
},
],
multiSelect: false,
},
{
question: "Will your app use push notifications?",
header: "Push",
options: [
{
label: "Yes",
description: "Configure push notification credentials",
},
{
label: "No",
description: "Skip push notification setup",
},
{
label: "Later",
description: "I'll set this up later",
},
],
multiSelect: false,
},
],
});
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 · 576 lines · 20 tokens per session scan A 73fe58b21f0c
init is a command published in the GitHub repository rahulkeerthi/expo-toolkit (5 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 3,203 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.
init compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| initrahulkeerthi/expo-toolkit | Command | 5 | 5mo ago | MIT | A | 20 | Claude Code |
| erne-animateJubaKitiashvili/everything-react-native-expo | Command | 50 | 29d ago | MIT | A | 21 | Claude Code |
| react-nativegetsentry/toolkit | Command | 957 | yesterday | none | A | 0 | Claude Code |
| app-store-auditmjmirza/app-store-compliance | Command | 403 | yesterday | none | A | 35 | Claude Code |
| initialize-iosdefendend/Claude-ast-index-search | Command | 582 | 1mo ago | MIT | A | 18 | Claude Code |
| mobile-performance-checktungnk123/mobile-best-practices | Command | 22 | 7mo ago | MIT | A | 14 | Claude Code |
| kmp-update-design-systemronjunevaldoz/kmp-agent-skills | Command | 6 | 12d ago | none | A | 34 | Claude Code |