{"id":48646689,"url":"https://github.com/nguyenthienthanh/aura-frog","last_synced_at":"2026-04-13T10:01:47.499Z","repository":{"id":326273127,"uuid":"1103832116","full_name":"nguyenthienthanh/aura-frog","owner":"nguyenthienthanh","description":"Aura Frog — Claude Code plugin — 10 agents, 5-phase TDD workflow, 3-tier rules, 27 hooks. Stop prompting. Start shipping. 🐸","archived":false,"fork":false,"pushed_at":"2026-04-10T03:31:45.000Z","size":15128,"stargazers_count":16,"open_issues_count":0,"forks_count":2,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-10T05:21:17.620Z","etag":null,"topics":["ai-assisted-development","ai-for-developers","claude-code","code-quality","command-driven-development","context-engineering","developer-productivity","engineering-process","multi-agent-system","prompt-engineering","software-engineering","structured-workflow","tdd","technical-documentation"],"latest_commit_sha":null,"homepage":"https://ethannguyenlabs.xyz/aura-frog/","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nguyenthienthanh.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-11-25T11:50:43.000Z","updated_at":"2026-04-10T03:31:48.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/nguyenthienthanh/aura-frog","commit_stats":null,"previous_names":["nguyenthienthanh/ccpm-team-agents"],"tags_count":27,"template":false,"template_full_name":null,"purl":"pkg:github/nguyenthienthanh/aura-frog","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nguyenthienthanh%2Faura-frog","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nguyenthienthanh%2Faura-frog/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nguyenthienthanh%2Faura-frog/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nguyenthienthanh%2Faura-frog/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nguyenthienthanh","download_url":"https://codeload.github.com/nguyenthienthanh/aura-frog/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nguyenthienthanh%2Faura-frog/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31747178,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T09:16:15.125Z","status":"ssl_error","status_checked_at":"2026-04-13T09:16:05.023Z","response_time":93,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-assisted-development","ai-for-developers","claude-code","code-quality","command-driven-development","context-engineering","developer-productivity","engineering-process","multi-agent-system","prompt-engineering","software-engineering","structured-workflow","tdd","technical-documentation"],"created_at":"2026-04-10T05:28:32.157Z","updated_at":"2026-04-13T10:01:47.494Z","avatar_url":"https://github.com/nguyenthienthanh.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n![Aura Frog](assets/logo/github_banner.png)\n\n# Aura Frog\n\n### An Operating System for software engineering.\n\nThe most powerful plugin for **[Claude Code](https://docs.anthropic.com/en/docs/claude-code)** — 10 agents, 5-phase TDD workflow, self-healing memory, and multi-agent orchestration. One kernel. Zero untested code.\n\n[![Version](https://img.shields.io/badge/version-3.4.0-blue.svg)](docs/reference/CHANGELOG.md)\n[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)\n[![Claude Code](https://img.shields.io/badge/Claude%20Code-Plugin-purple.svg)](https://docs.anthropic.com/en/docs/claude-code)\n[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)\n\n**LLM OS architecture. Memory that heals itself. TDD that never skips.**\n\n**[Install in 30 seconds](#-install)** · **[See it in action](#-before--after)** · **[Why Aura Frog?](#-the-problem)**\n\n\u003c/div\u003e\n\n---\n\n## The Problem\n\nYou open Claude Code. You type a prompt. Claude writes code. You *hope* it works.\n\nNo structure. No tests. No quality gates. Every session starts from scratch. Every complex feature turns into prompt spaghetti.\n\n**You're the project manager, QA lead, and architect — all while trying to code.**\n\n## The Solution\n\nAura Frog treats Claude Code as an **Operating System** — Claude is the kernel, agents are processes, and the context window is managed RAM. You describe the feature. Aura Frog dispatches the right agent, enforces a 5-phase TDD workflow, and compresses context automatically so you never lose decisions.\n\n**You approve twice. Aura Frog handles the rest.**\n\n---\n\n## Before \u0026 After\n\n\u003ctable\u003e\n\u003ctr\u003e\u003cth width=\"450\"\u003e❌ Without Aura Frog\u003c/th\u003e\u003cth width=\"450\"\u003e✅ With Aura Frog\u003c/th\u003e\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\n\n```\nYou: \"Add user authentication\"\nClaude: *writes 500 lines of untested code*\nYou: \"Wait, that's not what I—\"\nClaude: *rewrites everything from scratch*\n```\n\n\u003c/td\u003e\n\u003ctd\u003e\n\n```\nYou: \"Add user authentication\"\n\n🐸 Phase 1: \"JWT or OAuth2? Here are trade-offs.\n   3 endpoints needed. Approve?\"\n\nYou: \"approve\"\n\n🐸 Phase 2-3: 5 tests → all GREEN.\n🐸 Phase 4-5: Reviewed. Documented. Done.\n```\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n**Result:** Production-ready code with tests, security review, and documentation — from a single prompt.\n\n---\n\n## Install\n\n```bash\n# In Claude Code (takes 30 seconds):\n/plugin marketplace add nguyenthienthanh/aura-frog\n/plugin install aura-frog@aurafrog\n```\n\nStart your first workflow:\n\n```bash\nworkflow:start \"Your task here\"\n```\n\n\u003cdetails\u003e\n\u003csummary\u003eOptional: Install the \u003ccode\u003eaf\u003c/code\u003e CLI for health checks outside Claude Code\u003c/summary\u003e\n\n```bash\n# In Claude Code:\nsetup:cli\n\n# Or manually:\nsudo ln -sf \"$HOME/.claude/plugins/marketplaces/aurafrog/scripts/af\" /usr/local/bin/af\n```\n\nThen use anywhere: `af doctor`, `af setup remote`, `af measure`.\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003eWorks on other platforms (skills-only mode)\u003c/summary\u003e\n\n| Platform | Install | What Works |\n|----------|---------|------------|\n| **Claude Code** | `/plugin marketplace add nguyenthienthanh/aura-frog` | Everything |\n| **OpenAI Codex** | `cp -r aura-frog/skills/* ~/.codex/skills/` | Skills + commands |\n| **Gemini CLI** | `cp -r aura-frog/skills/* ~/.gemini/skills/` | Skills + commands |\n| **OpenCode** | `cp -r aura-frog/skills/* .opencode/skills/` | Skills + commands |\n\nHooks, agent detection, and MCP servers are Claude Code exclusive.\n\n\u003c/details\u003e\n\n---\n\n## Why Teams Ship Faster With Aura Frog\n\n### 1. Every Feature Gets a TDD Workflow\n\nNo more \"write code and hope.\" Every feature follows RED → GREEN → REFACTOR automatically:\n\n```\n  ✋ Phase 1: Understand + Design    → You approve the plan\n  ⚡ Phase 2: Test RED               → Failing tests written\n  ✋ Phase 3: Build GREEN            → You approve the implementation\n  ⚡ Phase 4: Refactor + Review      → Auto quality + security check\n  ⚡ Phase 5: Finalize               → Docs + notifications\n```\n\nTwo approvals. Five phases. Zero untested code.\n\n### 2. The Right Expert for Every Task\n\n10 specialized agents activate automatically — no configuration:\n\n```\n\"Build a React dashboard\"     → frontend\n\"Optimize the SQL queries\"    → architect\n\"Set up CI/CD pipeline\"       → devops\n\"Fix the login screen crash\"  → mobile\n\"Run a security audit\"        → security\n```\n\n\u003cdetails\u003e\n\u003csummary\u003eAll 10 agents\u003c/summary\u003e\n\n| Agent | When it activates |\n|-------|-------------------|\n| `lead` | Coordinates workflows, team orchestration |\n| `architect` | System design, databases, backend (Node, Python, Laravel, Go) |\n| `frontend` | React, Vue, Angular, Next.js + design systems |\n| `mobile` | React Native, Flutter, Expo, NativeWind |\n| `strategist` | ROI evaluation, MVP scoping, scope creep detection |\n| `security` | OWASP audits, vulnerability scanning, SAST |\n| `tester` | Jest, Cypress, Playwright, Detox, coverage |\n| `devops` | Docker, K8s, CI/CD, monitoring |\n| `scanner` | Project detection, config, context |\n| `router` | Agent + model selection |\n\n\u003c/details\u003e\n\n### 3. Complex Features Get Debated Before Built\n\nFor deep tasks, 4 agents independently analyze your plan — then challenge each other:\n\n```\n📐 Architect    → \"How to build it\"\n🔍 Tester       → \"How it can fail\"\n👤 Frontend     → \"How users experience it\"\n💼 Strategist   → \"Should we even build this?\"\n```\n\nPlans survive 4 rounds of scrutiny before a single line of code. Catches scope creep and wasted effort *before* it happens.\n\n### 4. Your Codebase Loads in Seconds, Not Minutes\n\nRun `project:init` once. Every future session instantly understands your codebase — conventions, architecture, patterns, file relationships. 12 pattern detections. 7 context files generated.\n\n**No more re-explaining your project every session.**\n\n### 5. Multi-Agent Teams for Big Features\n\nFor complex work, Aura Frog spins up a real team working in parallel:\n\n```\nlead\n├── architect     → Designs the system\n├── frontend      → Builds the UI\n├── tester        → Writes tests\n└── security      → Reviews for vulnerabilities\n\nAll cross-reviewing each other's work.\n```\n\nOnly activates when needed. Simple tasks stay single-agent (saves ~3x tokens).\n\n### 6. Context-Aware MCP Servers — Zero Config\n\n6 bundled servers auto-invoke when Claude needs them:\n\n```\n\"Build with MUI\"          → context7 fetches current MUI docs\n\"Test the login page\"     → playwright launches a browser\n\"Check test coverage\"     → vitest runs your suite\n\"Deploy to Firebase\"      → firebase manages the project\n```\n\nPlus Figma design fetching and Slack notifications.\n\n\u003cdetails\u003e\n\u003csummary\u003eMore features\u003c/summary\u003e\n\n#### Self-Improving Learning\nDetects your patterns, remembers corrections, creates rules that persist across sessions. Optional Supabase sync for teams.\n\n#### Smart Complexity Routing\nAutomatically matches effort to task size — typos get direct edits, features get full workflows, architecture gets collaborative planning. No configuration.\n\n#### Built-in Safety Net\nWorkflow crashed? `workflow:resume`. Context full? Decisions preserved across `/compact`. Need to pause? `workflow:handoff` saves everything.\n\n#### Memory That Heals Itself\nAll cached context is treated as a hint — agents verify against actual files before acting. State only updates after confirmed success (Strict Write Discipline). No stale assumptions propagate.\n\n#### 3-Tier Context Compression\nMicroCompact (free, every 10 turns) → AutoCompact (one /compact call at 80%) → ManualCompact (full session snapshot). Context stays lean. Decisions survive.\n\n#### Performance by Design\n3-tier rule loading (~75% less context), conditional hooks (~40% fewer executions), agent detection caching, session start caching (\u003c1s repeat sessions).\n\n\u003c/details\u003e\n\n---\n\n## The Numbers\n\n| Component | Count | Why it matters |\n|-----------|:-----:|----------------|\n| **Agents** | 10 | Right expert auto-selected per task |\n| **Skills** | 44 | 8 auto-invoke on context, 36 on-demand |\n| **Commands** | 26 | 10 bundled + 16 standalone — 71% consolidated |\n| **Rules** | 45 | 3-tier loading — only what's needed per phase |\n| **Hooks** | 28 | Conditional — skip processing for non-code files |\n| **MCP Servers** | 6 | Zero-config, auto-invoked |\n\nFull workflow target: **≤30K tokens** across all 5 phases.\n\n---\n\n## Workflow Modes\n\n| Mode | Command | Best for |\n|------|---------|----------|\n| **Full Workflow** | `workflow:start \"task\"` | New features, production code |\n| **Fast-Track** | `fasttrack: \u003cspecs\u003e` | Pre-approved specs |\n| **Quick Fix** | `bugfix:quick \"fix\"` | Small bugs with TDD |\n| **Refactor** | `refactor \"file\"` | Code cleanup |\n\n---\n\n## Documentation\n\n| | |\n|---|---|\n| **All Documentation** | [docs/README.md](docs/README.md) |\n| **Getting Started** | [GET_STARTED.md](docs/getting-started/GET_STARTED.md) |\n| **First Workflow Tutorial** | [FIRST_WORKFLOW_TUTORIAL.md](docs/getting-started/FIRST_WORKFLOW_TUTORIAL.md) |\n| **All Commands (26)** | [commands/README.md](aura-frog/commands/README.md) |\n| **All Skills (44)** | [skills/README.md](aura-frog/skills/README.md) |\n| **Agent Teams Guide** | [AGENT_TEAMS_GUIDE.md](docs/guides/AGENT_TEAMS_GUIDE.md) |\n| **MCP Setup** | [MCP_GUIDE.md](docs/operations/MCP_GUIDE.md) |\n| **Hooks \u0026 Lifecycle** | [hooks/README.md](aura-frog/hooks/README.md) |\n| **Troubleshooting** | [TROUBLESHOOTING.md](docs/operations/TROUBLESHOOTING.md) |\n| **Changelog** | [CHANGELOG.md](docs/reference/CHANGELOG.md) |\n\n---\n\n## Architecture — LLM OS\n\n```\nClaude = Kernel          Context Window = RAM           Project Files = Disk\nAgents = Processes       5-Phase TDD = Scheduler        MCP = Device Drivers\nTOON = Compression       Approval Gates = Interrupts    Handoffs = IPC\n\naura-frog/\n├── agents/         10 processes (auto-dispatched per task)\n├── skills/         44 skills (8 auto-invoke + 36 on-demand)\n├── commands/       26 commands (10 bundled + 16 standalone)\n├── rules/          45 rules (13 core + 15 agent + 17 workflow)\n├── hooks/          28 lifecycle hooks (conditional execution)\n├── scripts/        43 utility scripts\n├── docs/           AI reference docs (phases, TOON refs)\n└── .mcp.json       6 device drivers (MCP servers)\n```\n\n---\n\n## Contributing\n\nWe welcome contributions — especially new MCP integrations, agents, skills, and bug fixes. See [CONTRIBUTING.md](CONTRIBUTING.md) or submit an issue.\n\n\u003e Godot and SEO/GEO modules available as separate addons.\n\n---\n\n## License\n\nMIT — See [LICENSE](LICENSE)\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n![Aura Frog](assets/logo/mascot_coding_scene.png)\n\n### Your AI writes code. Aura Frog runs the OS.\n\n**[Install Now](#-install)** · **[Tutorial](docs/getting-started/FIRST_WORKFLOW_TUTORIAL.md)** · **[Report Issue](https://github.com/nguyenthienthanh/aura-frog/issues)**\n\n*Built by [@nguyenthienthanh](https://github.com/nguyenthienthanh) · [Changelog](docs/reference/CHANGELOG.md)*\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnguyenthienthanh%2Faura-frog","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnguyenthienthanh%2Faura-frog","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnguyenthienthanh%2Faura-frog/lists"}