AGENTS-REFERENCE

A reference file for a 20-agent system for Expo and React Native development. It lists included agents and describes additional agents that can be created.

In plain words
What is it for?
Use it to look up agents for architecture, design tokens, accessibility, testing, performance, and security, or to guide creation of agents such as package-compatibility checks.
Why use it?
It gives developers a single place to see which specialized agents exist and what kinds of work they cover. It also helps identify gaps where another agent may be needed.

Agent

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.

agentmods
npx agentmods add agents/senaiverse/reactnative-expo-ai-agent-system-workflow/agents-reference
Clone the repo
git clone --depth 1 https://github.com/senaiverse/reactnative-expo-ai-agent-system-workflow
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,292 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01292
Opus 5 $0.00000 $0.00646
Sonnet 5 $0.00000 $0.00258
Haiku 4.5 $0.00000 $0.00129

Measured 3d ago against content hash e3dcc053587b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AGENTS-REFERENCE 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 3d 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.

ready-to-use/agents/AGENTS-REFERENCE.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Reference & Expansion Guide

🌟 Created by SenaiVerse Claude Code Agent System for Expo/React Native Development

This file lists all 20 agents in the complete system. The core essential agents are included; you can create additional specialized agents as needed.


✅ Included Agents (Ready to Use)

Tier S: Meta Orchestration

  • grand-architect - Meta-orchestrator for complex features

Tier 1: Daily Workflow

  • design-token-guardian - Design system enforcement
  • a11y-enforcer - Accessibility compliance
  • test-generator - Smart test generation
  • performance-enforcer - Performance budget tracking

Tier 2: Power Agents

  • performance-prophet - Predictive performance analysis
  • security-specialist - Security penetration testing

📝 Additional Agents (Create as Needed)

You can create these agents following the same pattern as the included ones:

Tier 1: Daily Workflow

  • version-shield - Package compatibility checking
    • What it does: Validates package.json changes against React Native compatibility matrix
    • Tools: Read, Bash, WebFetch
    • Model: Sonnet

Tier 2: Power Agents

  • journey-cartographer - User flow mapping and edge case detection

    • What it does: Maps complete user journeys, identifies edge cases
    • Tools: Read, Grep, Glob
    • Model: Opus
  • refactor-surgeon - Zero-breaking refactoring

    • What it does: Large-scale refactoring with rollback strategies
    • Tools: Read, Edit, Grep, Bash
    • Model: Opus
  • cross-platform-enforcer - iOS/Android consistency

    • What it does: Ensures UX parity across platforms
    • Tools: Read, Bash, Grep
    • Model: Sonnet

Tier 3: Specialized

  • api-guardian - Type-safe API integration
  • memory-detective - Memory leak detection
  • design-enforcer - Design system validation
  • debt-quantifier - Technical debt measurement
  • test-architect - Test strategy planning
  • bundle-assassin - Bundle size optimization
  • migration-strategist - Safe version upgrades
  • state-auditor - State management analysis
  • impact-analyzer - Feature impact prediction

Read the full file on GitHub · 209 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. 3d ago First seen · 209 lines · 0 tokens per session scan A e3dcc053587b

Subscribe to this mod's changes

AGENTS-REFERENCE is an agent published in the GitHub repository senaiverse/reactnative-expo-ai-agent-system-workflow (125 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,292 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.

Related

Other agents, from other repositories

layer1-patterns

Layer 1 scans the codebase for UI entry points - places where users can trigger navigation, sheets, or actions. The goal is to create a complete inventory of "things users can tap.".

Terryc21/workflow-audit · 0 tokens

mobile

React Native / Flutter / Expo mobile development. Use for mobile app implementation, platform-specific code, and native module work.

nguyenthienthanh/aura-frog · 26 tokens

build-doctor

Native build failure specialist for React Native projects. Delegate when an iOS or Android build fails and the fix may take several investigation rounds, or when a long build log needs to be dug through without flooding the main conversation.

AnilBurcu/claude-code-react-native · 48 tokens

crash-analyst

Production crash and error-report investigator for React Native apps. Delegate when there is a Sentry event, a minified Hermes stack trace, a tombstone, or a user-reported crash to trace back to source and root cause.

AnilBurcu/claude-code-react-native · 52 tokens

perf-auditor

Read-only performance auditor for React Native codebases. Delegate when the app feels slow and the code should be swept for list, re-render, animation and startup antipatterns without making any edits.

AnilBurcu/claude-code-react-native · 44 tokens

release-checker

Pre-submission auditor for React Native releases. Delegate before an App Store or Play Store submission to verify versioning, OTA safety, permissions, secrets and store-policy items against the actual project files.

AnilBurcu/claude-code-react-native · 43 tokens