A Claude Code plugin for full-stack development, offering modes for building, fixing, reviewing and deploying code, plus layered security hooks and token budget monitoring to manage context use.
Claude Code
$ npx -y skills add smorky850612/Aurakit --agent claude-code
Codex
$ npx skills add smorky850612/Aurakit -a codex
Cursor
$ npx skills add smorky850612/Aurakit -a cursor
Gemini CLI
$ npx skills add smorky850612/Aurakit -a gemini-cli
GitHub Copilot
$ npx skills add smorky850612/Aurakit -a github-copilot
OpenCode
$ npx skills add smorky850612/Aurakit -a opencode
Windsurf
$ npx skills add smorky850612/Aurakit -a windsurf
Before & AfterΒ Β Β·Β Β Quick StartΒ Β Β·Β Β 46 ModesΒ Β Β·Β Β TiersΒ Β Β·Β Β PipelineΒ Β Β·Β Β SecurityΒ Β Β·Β Β New in v6.5Β Β Β·Β Β Why AuraKitΒ Β Β·Β Β FAQ
One command. Full-stack app. Production-ready.
AuraKit is a Claude Code skill that replaces 20+ manual instructions with a single /aura command. It auto-detects what you need, scans your project, generates code with security checks on every file, and commits β all in one shot.
npx @smorky85/aurakit # Install once (~30 seconds, auto-installs jq)
/aura build: login with JWT # That's it. AuraKit handles the rest.
Tip 30-second install β
npx @smorky85/aurakitorbash install.sh(v2.0), then type/aurain any project. jq, Python, and git are auto-detected and installed if missing.
You: "Build a login API"
Claude: *generates code*
You: "Wait, add input validation"
Claude: *regenerates*
You: "You forgot error handling"
Claude: *patches*
You: "Check for SQL injection"
Claude: *patches again*
You: "Now write tests"
Claude: *generates tests*
You: "The types are wrong..."
(30 min later, still going)
/aura build: login with JWT
# AuraKit automatically:
# β Scans your project stack (Scout/Haiku)
# β Plans file-by-file build order
# β Generates with SEC-01~15 rules
# β Validates types + security + tests
# β Commits: feat(auth): add login
# Done. One command. ~3 minutes.
1 β Install (choose one)
# macOS (Homebrew)
brew install smorky85/tap/aurakit
# All platforms (npm)
npx @smorky85/aurakit
# One-liner (macOS / Linux)
curl -fsSL https://raw.githubusercontent.com/smorky850612/Aurakit/main/install.sh | bash
# Windows
npx @smorky85/aurakit
# From source
bash install.sh
Note All install methods auto-activate L3~L5 security hooks. install.sh v2.0 auto-detects and installs:
jq(winget/scoop/choco/brew/apt/dnf/yum/apk/pacman), checks Node.js, Python, and git. Configures settings.json via Python-first (jq fallback). Installs the AuraKit Nexus status bar.
2 β Use
# Recommended for daily use (hooks enforce security without per-action dialogs)
claude --dangerously-skip-permissions
/aura build: login with JWT # BUILD mode (English)
/aura λ‘κ·ΈμΈ κΈ°λ₯ λ§λ€μ΄μ€ # BUILD mode (Korean Β· auto-detect)
/aura fix: TypeError in auth.ts # FIX mode
/aura μ½λ μ 리ν΄μ€ # CLEAN mode
/aura Vercel λ°°ν¬ μ€μ ν΄μ€ # DEPLOY mode
/aura μ½λ 리뷰ν΄μ€ # REVIEW mode
/aura! λ²νΌ μμ λ³κ²½ # QUICK mode Β· ~60% fewer tokens
Warning What
--dangerously-skip-permissionsmeans: Claude won't ask for confirmation on each tool use. This is intentional β AuraKit's hooks (bash-guard.js,security-scan.sh) replace per-action dialogs with automated enforcement. Withoutinstall.sh, security relies only on L1/L2 (agent role isolation + tool blocklist).Safer first-time alternative: Run
claudewithout the flag. Claude will ask for permission on each Write/Edit/Bash call.
Important Security rules in
~/.claude/rules/aurakit-security.mdare always active β applied to every Claude Code session automatically, even without running/aura.
3 β Update (existing users)
# Recommended β always fetches the latest version from npm
npx @smorky85/aurakit@latest
# From source (if you cloned the repo)
git pull origin main && bash install.sh
# One-liner (macOS / Linux)
curl -fsSL https://raw.githubusercontent.com/smorky850612/Aurakit/main/install.sh | bash
Tip Running the update command re-runs
install.shautomatically β hooks, skills, and security rules are all refreshed in place. Your.aura/project data (memory, instincts, snapshots) is never overwritten.
AuraKit enforces these 8 principles in every mode, every turn, every output. Any response that violates them is not AuraKit.
| # | Principle | Guarantee | Mechanism |
|---|---|---|---|
| 1 | β‘ FAST | Faster than any skill | Session cache Β· ConfigHash Β· QUICK mode Β· Progressive Load |
| 2 | β¨ FLASHY | Most informative CLI output | StatusLine Β· Next Actions Β· Token Report Β· Pipeline display |
| 3 | π SECURE | Genuinely top-tier security | 6-layer gates Β· 10 hooks Β· SEC-01~15 Β· bash-guard Β· security-scan |
| 4 | π° THRIFTY | Max token savings even on Opus | Tiered Model Β· Fail-Only output Β· Progressive Load Β· Session cache |
| 5 | βΎοΈ IMMORTAL | Survives context loss | 65% compact guard Β· Snapshots Β· PostCompact restore Β· Session resume |
| 6 | π§ EVOLVING | Gets smarter with every use | Instinct learning Β· instinct:evolve Β· Pattern sharing |
| 7 | π UNIVERSAL | Any platform, any language | 8 languages Β· 46 modes Β· 23 agents Β· 5 platforms Β· Non-dev QUICK mode |
| 8 | π TOP-TIER | Best skill, no comparison | Sum of the above 7 |
"I can just prompt Claude myself" β Yes, but you'll repeat the same 20 instructions every session.
| Manual Prompting | CLAUDE.md File | AuraKit v6.5.0 | |
|---|---|---|---|
| Security enforcement | Hope for the best | Rules, no enforcement | 10 hooks enforce at write-time |
| Context survival | Lost on compact | Partial | Snapshot + PostCompact auto-restore |
| Token efficiency | Wasteful | Manual | ~55% ECO Β· ~75% MAX (estimated) |
| Code review | Manual | Manual | 4 agents in parallel |
| Multi-language | English only | English only | 8 languages Β· 56+ commands |
| Learns over time | Starts fresh | Starts fresh | Instinct engine auto-saves patterns |
| jq / tools | Manual setup | Manual setup | Auto-installed on first run |
| Install time | β | 30 min writing rules | ~30 seconds |
AuraKit detects your intent from natural language. Use a namespace prefix (build:, fix:) when the mode is ambiguous.
| Mode | Invoke | What It Does |
|---|---|---|
| BUILD | /aura build: ... or just describe it | Discovery β micro-plan β generate β triple verify β commit |
| FIX | /aura fix: ... or paste the error | Root-cause analysis β minimal change β verify |
| REVIEW | /aura review: | 4 parallel agents β VULN-NNN report, AβF grade |
| CLEAN | /aura clean: | Dead code removal, 250-line splits, deduplication |
| DEPLOY | /aura deploy: | Framework detect β env setup β deploy config β security recheck |
π 40 Extended Modes β Quality Β· Planning Β· Platform Β· Utility Β· Autopus-ADK Β· Auto
Quality & Testing
| Mode | Trigger | What It Does |
|---|---|---|
| GAP | gap:, match rate | Design β implementation gap analysis (Match Rate %) |
| ITERATE | iterate:, auto-fix | Auto-improve until Match Rate β₯ 90% (max 5 cycles) |
| TDD | tdd:, test-first | π΄ RED β π’ GREEN β π΅ REFACTOR Β· coverage β₯ 70β90% |
| QA | qa:, docker logs | Zero-Script QA via real Docker log analysis |
| QA:E2E | qa:e2e:setup | Playwright E2E β auth / CRUD / responsive / CI pipeline |
| DEBUG | debug:, 5-why | 4-phase systematic debugging with root-cause tracing |
Planning & Design
| Mode | Trigger | What It Does |
|---|---|---|
| PM | pm:, PRD, discovery | OST + JTBD + Lean Canvas + PRD Β· 5 PM agents in parallel |
| PLAN | plan:, κ³ν | Structured plan β .aura/docs/plan-*.md |
| DESIGN | design:, DB μ€κ³ | DB + API + UI workers parallel β cross-consistency check |
| REPORT | report:, μλ£ λ³΄κ³ μ | 4-perspective value report (user/biz/tech/ops) |
| PIPELINE | pipeline:, κ°λ° μμ | 9-phase guide: Starter / Dynamic / Enterprise |
| BRAINSTORM | brainstorm:, HMW | HMW + priority matrix β actionable ideas |
Advanced Operations
| Mode | Trigger | What It Does |
|---|---|---|
| ORCHESTRATE | orchestrate:, leader | Leader / Swarm / Council / Watchdog multi-agent patterns |
| BATCH | batch:[A,B,C] | Up to 5 features in parallel Git Worktrees |
| LOOP | batch:loop: until:pass | Autonomous iteration loop until condition met |
| FINISH | finish:, squash | Branch squash merge + Worktree cleanup |
| ARCHIVE | archive:, archive:list | Archive features without deleting |
Platform Specialists
| Mode | Trigger | What It Does |
|---|---|---|
| MOBILE | mobile:, react native | React Native / Expo specialized pipeline |
| DESKTOP | desktop:, electron | Electron / Tauri specialized pipeline |
| BAAS | baas:, supabase | Supabase / Firebase / bkend integration guide |
| PAYMENT | payment:, stripe, polar, toss | Stripe Β· LemonSqueezy Β· Polar Β· TossPayments Β· StepPay β full subscription billing pipeline (default PRO tier) |
Intelligence & Configuration
| Mode | Trigger | What It Does |
|---|---|---|
| INSTINCT | instinct:show | View / manage / evolve learned project patterns |
| LANG | lang:python, lang:go | Force language-specific code reviewer (10 languages) |
| MCP | mcp:setup, mcp:list | Install & configure 14 MCP server types |
| CONTENT | content:, λΈλ‘κ·Έ | Blog, market research, IR deck, tech docs, email, social |
| STATUS | status, νμ¬ μν | Current work state from .aura/snapshots/ |
| STATUS:HEALTH | status:health | Health Dashboard β Match Rate Β· security score Β· coverage Β· Tech Debt |
| CONFIG | config:set | Manage .aura/config.json settings |
Utility
| Mode | Trigger | What It Does |
|---|---|---|
| STYLE | style:, learning | Switch output persona: learning / expert / concise |
| SNIPPETS | snippets:, μ€λν« | Save and reuse prompt templates |
QUICK (!) | /aura! request | Protocol-minimal, single file, ~60% token savings |
Stars on GitHub
A development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
@obraHelps you take a change from a rough idea or bug report through to a tested, reviewed result, with each step handled by a focused skill. Its skills cover pinning down domain terms, designing module interfaces, diagnosing hard bugs, and reviewing changes against your repo's coding standards.
@mattpocockGives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
@affaan-mDeveloper tools for working on the React codebase itself. Provides skills for extracting error messages, managing and debugging feature flags across release channels, running Flow type checks, and fixing lint and formatting issues before committing.
@facebookA Claude Code plugin for full-stack development, offering modes for building, fixing, reviewing and deploying code, plus layered security hooks and token budget monitoring to manage context use. Install it with the command on its page. It includes aura-compact, aura-guard, aura. Its skills do not fire on their own yet. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it