Package Exports
This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (erne-universal) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.
Readme
๐๏ธ ERNE โ Everything React Native & Expo
The complete AI coding agent harness for React Native and Expo โ 11 specialized agents, adaptive stack detection, multi-agent orchestration, and a pixel-art dashboard. Every config is generated to match your exact project setup.
โก Quick Start
Prerequisite: Claude Code is required for the full experience (11 agents, pipeline orchestration, dashboard, hooks). Other IDEs receive adaptive rules and configuration โ see IDE Support.
npx erne-universal initThis will:
- ๐ Deep-scan your project โ detects 15 stack dimensions (state management, navigation, styling, lists, images, forms, storage, testing, build system, component style, monorepo, New Architecture, and more)
- ๐๏ธ Let you choose a hook profile (minimal / standard / strict)
- ๐ Select MCP integrations (simulator control, GitHub, etc.)
- โ๏ธ Generate adaptive configuration โ selects from 24 variant templates matched to your exact stack (Zustand vs Redux, Expo Router vs React Navigation, NativeWind vs StyleSheet, etc.)
๐ฆ What's Included
| Component | Count | Description |
|---|---|---|
| ๐ค Agents | 11 | Specialized AI agents for architecture, development, review, testing, UI, native, orchestration |
| ๐ Agent variants | 9 | Stack-adaptive agent configurations (StyleSheet vs NativeWind, Zustand vs Redux, etc.) |
| โก Commands | 19 | Slash commands for every React Native workflow |
| ๐ Rule layers | 5 | Conditional rules: common, expo, bare-rn, native-ios, native-android |
| ๐ฏ Rule variants | 15 | Stack-specific rules selected by deep detection (state, navigation, styling, security, etc.) |
| ๐ก๏ธ Hook profiles | 3 | Minimal, standard, strict โ quality enforcement your way |
| ๐ Skills | 7 | Reusable knowledge modules loaded on-demand |
| ๐ญ Contexts | 3 | Behavior modes: dev, review, vibe |
| ๐ MCP configs | 10 | Pre-configured server integrations |
| ๐ Workflow examples | 4 | End-to-end multi-agent workflow guides |
| ๐ค Handoff templates | 4 | Structured agent-to-agent context passing |
๐ฎ Agent Dashboard
ERNE includes a real-time pixel-art dashboard with 4 tabs, a context sidebar, and animated office visualization.
erne dashboard # Start on port 3333, open browser
erne dashboard --port 4444 # Custom port
erne dashboard --no-open # Don't open browser
erne start # Init project + dashboard in backgroundHQ โ Pixel-Art Office
- ๐ข 4 office rooms โ Development, Code Review, Testing, and Conference
- ๐จ 11 animated agent sprites with walking, typing, and done animations
- ๐ฌ Thought bubbles showing the current task above working agents
- ๐ฅ๏ธ Animated monitor screens (green code when working, screensaver when idle)
- ๐ Toast notifications for agent start/complete events
- ๐ Bottom stats bar with session duration, tasks completed, working/planning counts
- ๐ค Agent detail overlay with full activity history (click any agent)
- ๐ฏ Pipeline orchestrator coordination view in conference room
- ๐ Real-time WebSocket updates with auto-reconnect
My App โ Project Intelligence
- ๐ App overview with framework detection, health grade, and stack chips
- ๐ 10 MCP integration statuses with requirements
- ๐ Project audit with score, findings (with FIX buttons), and strengths
- โก Quick actions โ run tests, lint, start dev, build iOS/Android, pod install
- ๐ก Smart recommendations based on audit findings
- ๐ ๏ธ Environment checks for all dev tools (Node, Xcode, CocoaPods, etc.)
Ecosystem โ Release Radar
- ๐ฐ Live release feed for React Native ecosystem packages
- ๐ท๏ธ Tags: NEW, BREAK, security patches
- ๐ Filter by category: Updates, Trending, Tips, Security
- ๐ Quick stats sidebar
Insights โ Project Analytics
- ๐ KPI cards: Audit Score, Outdated Deps, Agent Tasks (with deltas)
- ๐ Agent utilization breakdown with horizontal bar chart
Context Sidebar
The sidebar auto-enables with the dashboard and provides 6 collapsible panels:
- ๐ฅ๏ธ System Info โ project metadata, environment checks, git branch
- ๐ Project Audit โ 22-point score with one-click FIX buttons and strength checks
- ๐ Agent Activity โ real-time task history with timestamps
- ๐พ Context Savings โ live savings percentage, KB saved, and event timeline
- ๐ Knowledge Base โ FTS5-powered search across 5 categories (pattern, decision, error, api, component)
- ๐ฐ Context Budget โ set session/agent token limits, choose overflow strategy (truncate / warn / stop)
Context optimization runs automatically โ no flags or configuration needed. See Context Optimization for details.
๐ฏ Multi-Agent Orchestration
ERNE supports coordinated multi-agent workflows through the pipeline orchestrator:
/orchestrate "build user profile screen"Pipeline phases:
๐๏ธ Plan architect decomposes the task
โ
โก Implement senior-developer + feature-builder (parallel)
โ
๐งช Test tdd-guide writes and runs tests
โ
๐ Review code-reviewer validates with evidence
โ
๐ Validate performance-profiler checks performanceFeatures retry logic (max 3 attempts), escalation to user on persistent failures, and structured handoff templates for context passing between agents. See Pipeline Documentation for details.
๐ค Agents
Each agent has a distinct personality, quantified success metrics, and memory integration for cross-session learning.
| Agent | Emoji | Domain | Room |
|---|---|---|---|
| architect | ๐๏ธ | System design and project structure | Development |
| senior-developer | ๐จโ๐ป | End-to-end feature implementation, screens, hooks, API | Development |
| feature-builder | โก | Focused implementation units, works in parallel | Development |
| native-bridge-builder | ๐ | Turbo Modules and native platform APIs | Development |
| expo-config-resolver | โ๏ธ | Expo configuration and build issues | Development |
| ui-designer | ๐จ | Accessible, performant UI components | Development |
| code-reviewer | ๐ | Code quality with evidence-based approval | Code Review |
| upgrade-assistant | ๐ฆ | Version migration guidance | Code Review |
| tdd-guide | ๐ฆ | Test-driven development workflow | Testing |
| performance-profiler | ๐๏ธ | FPS diagnostics and bundle optimization | Testing |
| pipeline-orchestrator | ๐ฏ | Multi-agent workflow coordination | Conference |
๐ง Context Optimization
ERNE includes a built-in context intelligence system that reduces tool output bloat by 97โ100%, preserves exact code examples via FTS5 search, and manages your context budget โ all auto-enabled with the dashboard.
erne dashboard # Context system starts automaticallyBenchmark-verified savings
| Layer | What it does | Savings |
|---|---|---|
| Summarizer | Auto-detects 14 content types (docs, JSON, logs, test output, build output, CSV, git history, etc.) and compresses to statistical summaries | 97โ100% |
| Index + Search | Chunks content by headings, indexes in FTS5 with BM25 ranking. Returns only relevant chunks โ code examples preserved exactly | 80% |
| Full session | Combined summarizer + search across a real debugging session (docs, snapshots, issues, tests, builds) | 99% |
Real numbers: 537 KB of tool outputs โ 2.6 KB of context. That's 0.4% of a 200K context window instead of 44.5%. See BENCHMARK.md for the full 21-scenario breakdown.
How it works
Tool Output โโโถ Smart Summarizer โโโถ 97-100% compression (14 content types)
โ
Raw Docs โโโถ FTS5 Index+Search โโโถ 80% savings, exact code preserved
โ
Session Events โโโถ Session Tracker โโโถ ErrorโFix correlation
โ
Knowledge โโโถ 3-Layer Search (FTS5 โ Trigram โ Levenshtein)
โ
Session End โโโถ Snapshot (<2KB) โโโถ Next session restores context| Feature | What it does |
|---|---|
| Content summarizer | 14 auto-detected content types: markdown, HTML, JSON, test output, TypeScript errors, build output, logs, git history, CSV, and more. Each type gets a specialized summary format |
| Content store | FTS5-powered index with Porter stemming. Markdown chunked by headings, code blocks never split or truncated. BM25 relevance ranking with byte budget management |
| Smart truncation | 4-tier fallback cascade: Structured โ Pattern โ Head/Tail โ Hash. Handles anything the summarizer doesn't cover |
| Knowledge base | SQLite-backed with FTS5 full-text search, trigram fuzzy matching, and Levenshtein fallback. Entries scored by recency + access frequency |
| Session continuity | Snapshots capture active tasks, decisions, errors, and commits at session end. Next session restores context in <2KB |
| Budget manager | Set per-session and per-agent token limits. Throttles at 80%, supports aggressive truncation / warn / hard stop overflow strategies |
| Agent preloader | Tracks agent-to-agent transitions and predicts the next agent for parallel context warmup |
| ErrorโFix tracking | Correlates errors with subsequent file modifications to build fix patterns over time |
Dashboard sidebar panels
The context sidebar (toggle with the chevron button) shows 6 live panels:
- System Info โ project metadata, environment health, git branch
- Project Audit โ 22-point audit with score, one-click FIX buttons, and strengths
- Agent Activity โ real-time task history with timestamps
- Context Savings โ live savings percentage, KB saved, and event timeline
- Knowledge Base โ searchable entries with category filters (pattern, decision, error, api, component)
- Context Budget โ configure session limits and overflow strategy directly from the UI
If the context system is disabled, the sidebar shows an Enable Context button to activate it at runtime.
๐ฐ Token Efficiency
ERNE minimizes token usage through two complementary systems: architecture-level savings (what gets loaded into context) and runtime context optimization (how tool outputs and session state are compressed).
Architecture savings
| Mechanism | How it works | Savings |
|---|---|---|
| Profile-gated hooks | Minimal profile runs 4 hooks instead of 16 | ~31% |
| Conditional rules | Only loads rules matching your project type (Expo, bare RN, native) | ~26% |
| On-demand skills | Skills load only when their command is invoked, not always in context | ~12% |
| Subagent isolation | Fresh agent per task with only its own definition + relevant rules | ~12% |
| Task-specific commands | 19 focused prompts instead of one monolithic instruction set | ~13% |
| Context-based behavior | Modes change behavior dynamically without loading new rulesets | ~3% |
Runtime context optimization (benchmark-verified)
| Mechanism | How it works | Savings |
|---|---|---|
| Content summarizer | Auto-detects 14 content types, produces statistical summaries | 97โ100% per output |
| Index + Search | FTS5 BM25 retrieval returns only relevant chunks, code preserved exactly | 80% per search |
| Smart truncation | 4-tier fallback: Structured โ Pattern โ Head/Tail โ Hash | 85โ100% per output |
| Session snapshots | Captures full session state in <2KB | ~50% vs log replay |
| Budget enforcement | Throttling at 80% prevents runaway token usage | Prevents overflow |
Result: Architecture saves 60โ67% on what enters context. Runtime optimization achieves 97โ100% compression on tool outputs (verified across 21 benchmark scenarios with 537 KB of real data). In a full debugging session, 99% of tool output tokens are eliminated โ leaving 99.6% of your context window free for actual problem solving. See BENCHMARK.md for complete results.
๐ก๏ธ Hook Profiles
| Profile | Hooks | Use Case |
|---|---|---|
minimal |
4 | โก Fast iteration, vibe coding โ maximum speed, minimum friction |
standard |
12 | โ๏ธ Balanced quality + speed (recommended) โ catches real issues |
strict |
16 | ๐ Production-grade enforcement โ full security, accessibility, perf budgets |
Change profile: set ERNE_PROFILE env var, add <!-- Hook Profile: standard --> to CLAUDE.md, or use /vibe context.
โก Commands
| Category | Commands |
|---|---|
| Core | /plan, /code-review, /tdd, /build-fix, /perf, /upgrade, /native-module, /navigate, /code, /feature |
| Extended | /animate, /deploy, /component, /debug, /quality-gate |
| Orchestration | /orchestrate |
| Learning | /learn, /retrospective, /setup-device |
๐ฅ๏ธ IDE & Editor Support
ERNE generates adaptive config files for multiple IDEs, but the full agent experience requires Claude Code:
| Feature | Claude Code | Cursor / Windsurf / Copilot / Codex |
|---|---|---|
| Adaptive rules & config | โ | โ |
| Stack detection (15 dimensions) | โ | โ |
| 19 slash commands | โ | โ |
| 11 specialized agents | โ | โ |
| Pipeline orchestration | โ | โ |
| Hook profiles | โ | โ |
| Agent dashboard | โ | โ |
| Cross-session memory | โ | โ |
Generated config files:
| File | IDE / Tool |
|---|---|
CLAUDE.md |
Claude Code (full experience) |
AGENTS.md |
Codex, Windsurf, Cursor, GitHub Copilot |
GEMINI.md |
Gemini CLI |
.cursorrules |
Cursor |
.windsurfrules |
Windsurf |
.github/copilot-instructions.md |
GitHub Copilot |
๐๏ธ Architecture
Claude Code Hooks โโโถ run-with-flags.js โโโถ Profile gate โโโถ Hook scripts
โ
โโโโโโโโโโโโดโโโโโโโโโโโ
โ Only hooks for โ
โ active profile โ
โ are executed โ
โโโโโโโโโโโโโโโโโโโโโโโ
erne dashboard โโโถ HTTP + WS Server โโโถ Browser Canvas
โฒ
Claude Code PreToolUse โโค (Agent pattern)
Claude Code PostToolUse โKey design principles:
- ๐ชถ Zero runtime dependencies for the harness itself (ws package only for dashboard)
- ๐ฏ Conditional loading โ rules, skills, and hooks load based on project type and profile
- ๐งน Fresh subagent per task โ no context pollution between agent invocations
- ๐ Silent failure โ hooks never block Claude Code if something goes wrong
๐ค Contributing
We welcome contributions from everyone โ from typo fixes to new agents and skills.
| I want to... | Start here |
|---|---|
| ๐ Report a bug | Bug Report |
| ๐ก Request a feature | Feature Request |
| ๐ Propose a new skill | Skill Proposal |
| ๐ Submit a PR | Contributing Guide |
git checkout -b feat/your-feature
npm run validate && npm test # Must pass before PR๐ค Partnerships
Skills, agents, and MCP configs are open source โ anyone can add them via PR. Partnerships are for deeper collaboration:
| Partnership Type | What It Means |
|---|---|
| Co-Maintenance | You keep your library's ERNE skill up to date as your API evolves |
| Early Access | We update ERNE before your breaking changes ship, so users never hit stale guidance |
| Joint Promotion | Your docs recommend ERNE for AI-assisted development, we feature you on erne.dev |
| Domain Expertise | Co-develop specialized agents that require deep knowledge of your platform |
If you maintain a React Native library, Expo tool, or developer service โ let's talk.
๐ฆ Available On
- npm โ
npx erne-universal init - SkillsMP โ Auto-indexed from GitHub
- BuildWithClaude โ Plugin directory
- VoltAgent/awesome-agent-skills โ Curated skills list
๐ Documentation
| Doc | Description |
|---|---|
| Getting Started | Installation and first run |
| Agents Guide | All 11 agents with domains and usage |
| Commands Reference | All 19 slash commands |
| Hooks & Profiles | Hook system and 3 profiles |
| Creating Skills | Author your own skills |
| Pipeline & Orchestration | Multi-agent workflow coordination |
| Memory Integration | Cross-session learning with MCP |
| Handoff Templates | Structured agent-to-agent context |
| Contributing | How to contribute |
๐ License
MIT License โ use freely, commercially or personally.
๐๏ธ ERNE โ Your React Native AI Dream Team ๐๏ธ
โญ Star this repo ยท ๐ด Fork it ยท ๐ Report an issue ยท ๐ erne.dev
Made with โค๏ธ for the React Native community