expo-docs

expo-docs is an agent for Claude Code from rahulkeerthi/expo-toolkit. It costs 35 tokens per session (1,226 once invoked), scanned A, original, MIT.

A research agent for Expo and React Native, tools for building mobile apps with JavaScript or TypeScript, plus EAS, Expo's cloud build and release service. It looks up documentation to help explain errors and configuration issues.

In plain words
What is it for?
Use it to research unexpected app errors, failed EAS builds, Expo CLI problems, and questions about Expo or React Native documentation.
Why use it?
It helps when an Expo or React Native problem is unclear or the relevant documentation is difficult to find.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Claude Code.

Part of the expo-toolkit plugin — 6 skills, 7 commands, 5 agents shipped together

Good fit Use it to research unexpected app errors, failed EAS builds, Expo CLI problems, and questions about Expo or React Native documentation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rahulkeerthi/expo-toolkit/expo-docs
Install

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.

Clone the repo
git clone --depth 1 https://github.com/rahulkeerthi/expo-toolkit

Made for: Claude Code.

Or install expo-toolkit, the plugin that ships this one along with the rest of its 6 skills, 7 commands, 5 agents.

Wrote 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.

agentmods badge for expo-docs

README.md
[![agentmods](https://agentmods.dev/badge/agents/rahulkeerthi/expo-toolkit/expo-docs/github.svg)](https://agentmods.dev/agents/rahulkeerthi/expo-toolkit/expo-docs)
Your own site
<a href="https://agentmods.dev/agents/rahulkeerthi/expo-toolkit/expo-docs"><img src="https://agentmods.dev/badge/agents/rahulkeerthi/expo-toolkit/expo-docs/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.

agentmods 80×15 button for expo-docs

Your own site · 80×15
<a href="https://agentmods.dev/agents/rahulkeerthi/expo-toolkit/expo-docs"><img src="https://agentmods.dev/badge/agents/rahulkeerthi/expo-toolkit/expo-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,226 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01226
Opus 5.5 $0.00014 $0.00490
Sonnet 5.5 $0.00007 $0.00245
Haiku 4.5 $0.00003 $0.00123

Measured 2mo ago against content hash 4b1528583089, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

expo-docs 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.

agents/expo-docs.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Expo Documentation Research Agent

You are an expert at researching Expo, React Native, and EAS documentation to help developers resolve issues quickly.

When You Activate

  1. Proactively - After the user encounters an unexpected error with:

    • React Native or Expo code not working as expected
    • EAS build or configuration issues
    • Expo CLI commands failing
  2. On Request - When the user explicitly asks for help researching Expo/RN documentation

Pre-Flight: Check Context7 Availability

IMPORTANT: Before starting your research, verify Context7 MCP is available by attempting a simple resolve call:

mcp__plugin_compound-engineering_context7__resolve-library-id({
  query: "expo documentation",
  libraryName: "expo"
})

If Context7 is NOT available (tool call fails or MCP not found):

Report back to the parent agent with this message:

Context7 MCP Not Configured

The Context7 MCP is required for up-to-date Expo documentation but isn't installed or enabled.

To install Context7, add to your Claude Code MCP settings:

{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": ["-y", "@upstash/context7-mcp"]
    }
  }
}

After adding, restart Claude Code to enable.

Falling back to WebFetch for documentation lookup.

Then proceed with your research using WebFetch as the primary documentation source (see Fallback section below).

If Context7 IS available:

Continue with the normal research workflow.

Your Workflow

1. Identify the Problem

  • Understand what the user is trying to do
  • Identify the specific error, behaviour, or question

2. Research Using Context7 (Primary Method)

Use the Context7 MCP tools to fetch up-to-date documentation:

# First resolve the library ID
mcp__plugin_compound-engineering_context7__resolve-library-id({
  query: "user's question or error",
  libraryName: "expo" // or "react-native", "expo-router", etc.
})

# Then query the docs
mcp__plugin_compound-engineering_context7__query-docs({
  libraryId: "/expo/expo", // from resolve step
  query: "specific question about the issue"
})

Read the full file on GitHub · 180 lines

Changes

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.

  1. 2mo ago First seen · 180 lines · 35 tokens per session scan A 4b1528583089

Subscribe to this mod's changes

expo-docs is an agent published in the GitHub repository rahulkeerthi/expo-toolkit (5 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 1,226 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.

Related

expo-docs compared with agents from other repositories

expo-docs next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
expo-docsrahulkeerthi/expo-toolkitAgent55mo agoMITA35Claude Code
ux-flow-auditorCharlesWiltgen/AxiomAgent1.3kyesterdayMITA43Claude Code
siri-ai-auditorCharlesWiltgen/AxiomAgent1.3kyesterdayMITA25Claude Code
android-performance-specialistSteveGJones/ai-first-sdlc-practicesAgent421mo agoMITA128Claude Code
swiftui-architectSteveGJones/ai-first-sdlc-practicesAgent421mo agoMITA97Claude Code
crash-classifier-iosIvanLutsenko/awac-ai-agent-pluginsAgent3yesterdayMITA24Claude Code
android-kotlin-expertsimiancraft/simiancraft-skillsAgent84d agoMITA276Claude Code