Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rahulkeerthi/expo-toolkitnpx agentmods add skills/rahulkeerthi/expo-toolkit/building-with-easWrote 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/skills/rahulkeerthi/expo-toolkit/building-with-eas)<a href="https://agentmods.dev/skills/rahulkeerthi/expo-toolkit/building-with-eas"><img src="https://agentmods.dev/badge/skills/rahulkeerthi/expo-toolkit/building-with-eas/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/skills/rahulkeerthi/expo-toolkit/building-with-eas"><img src="https://agentmods.dev/badge/skills/rahulkeerthi/expo-toolkit/building-with-eas.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 | $0.00037 | $0.02757 |
| Opus 5.5 | $0.00015 | $0.01103 |
| Sonnet 5.5 | $0.00007 | $0.00551 |
| Haiku 4.5 | $0.00004 | $0.00276 |
Grade A, and why
building-with-eas 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 — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EAS Build & Submit Reference
Plugin Tools
Before production builds, verify your version hasn't already been released:
# Check version against EAS build history and store releases
cd /path/to/expo-toolkit && npm run check-version -- /path/to/your/app
# Or directly
node tools/check-version.js /path/to/your/app
node tools/check-version.js /path/to/your/app --json
This checks:
- Current version in app.config.js
- Recent EAS builds and their submission status
- autoIncrement settings in eas.json
- Provides guidance if version bump is needed
Essential Commands
# Initialize EAS in project
eas init
# Configure build profiles
eas build:configure
# Check/manage credentials
eas credentials
eas credentials --platform ios
eas credentials --platform android
# Build commands
eas build --platform ios --profile development
eas build --platform android --profile preview
eas build --platform all --profile production
# Build with auto-submit
eas build --platform ios --profile production --auto-submit
eas build --platform android --profile production --auto-submit
# Check build status
eas build:list
eas.json Configuration
Standard Build Profiles
The eas.json file defines build profiles. A well-configured file looks like:
{
"cli": {
"version": ">= 16.18.0",
"appVersionSource": "remote"
},
"build": {
"base": {
"env": {
"APP_VARIANT": "production"
}
},
"development": {
"extends": "base",
"developmentClient": true,
"distribution": "internal",
"env": {
"APP_VARIANT": "development"
},
"ios": {
"simulator": false
},
"android": {
"buildType": "apk",
"gradleCommand": ":app:assembleDebug"
}
},
"development-simulator": {
"extends": "development",
"ios": {
"simulator": true
},
"android": {
"buildType": "apk"
}
},
"preview": {
"extends": "base",
"distribution": "internal",
"env": {
"APP_VARIANT": "preview"
},
"android": {
"buildType": "apk"
}
},
"production": {
"extends": "base",
"autoIncrement": true,
"env": {
"APP_VARIANT": "production"
}
}
},
"submit": {
"production": {
"ios": {
"appleId": "[email protected]",
"ascAppId": "1234567890"
},
"android": {
"serviceAccountKeyPath": "./play-store-credentials.json",
"track": "internal"
}
}
}
}
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 · 486 lines · 37 tokens per session scan A b7504a2f4ae9
building-with-eas is a skill published in the GitHub repository rahulkeerthi/expo-toolkit (5 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 2,757 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.
building-with-eas compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| building-with-easrahulkeerthi/expo-toolkit | Skill | 5 | 5mo ago | MIT | A | 37 | Claude Code |
| agent-browserx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 39 | Claude Code, Codex |
| odevioOdevio/Odevio-CLI | Skill | 424 | 14d ago | MIT | A | 0 | Claude Code |
| fastly-compute-well-known-spa-fallbackdivinevideo/divine-mobile | Skill | 264 | yesterday | MPL-2.0 | A | 151 | Claude Code, Codex |
| expo-deploymentopenai/plugins | Skill | 7.8k | 3d ago | none | A | 24 | Codex |
| capawesome-cloudcapawesome-team/skills | Skill | 54 | 2d ago | MIT | A | 172 | Claude Code, Codex |
| google-mobile-ninjafabricioctelles/jump-skills | Skill | 32 | 2d ago | MIT | A | 115 | Claude Code, Codex |