By jaminitachi
Claude Code AI plugin — 36 MCP tools, 10 team agents, 11 skills, Mac automation, Telegram remote control, persistent memory, TDD-driven team orchestration
Quick one-line system health check
Quick heartbeat - run collectors and show compact report
Quick memory search command
Quick screenshot capture with optional Telegram send
Quick system health status dashboard
DEV team QA — TDD, unit/integration/e2e testing
INFRA team mac-control — screenshots, UI automation, app control
INFRA team monitor — system health, heartbeat, cron, pipelines
RESEARCH team assistant — citations, BibTeX, quick lookups
RESEARCH team reviewer — paper analysis, literature synthesis, data analysis, experiment tracking
Manage scheduled tasks via system crontab / node-cron
Developer productivity workflows - PR review, CI monitoring, deploy tracking, code metrics
Proactive system monitoring with 7 collectors, alerting, and Telegram notifications
Paper analysis (single or multi) with structured extraction, gap analysis, and citation graph
Full macOS automation via Peekaboo and AppleScript - screenshots, UI interaction, app control
Matches all tools
Hooks run on every tool call, not just specific ones
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Claude Code plugin for agentic Mac automation, persistent memory, Telegram remote control, and multi-agent orchestration.
SuperClaw turns Claude Code into a full autonomous workstation. One request auto-composes the right team of agents, executes in parallel, and verifies results independently.
36 MCP tools across 3 servers (bridge, peekaboo, memory)
10 team agents with 3-tier model routing (haiku / sonnet / opus)
9 skills with keyword auto-detection (Korean + English)
7 lifecycle hooks for context injection, tool enforcement, and session persistence
Smart team routing — complex requests auto-compose multi-agent teams
Sisyphus pattern — blocks session exit until autonomous tasks complete
Obsidian sync — exports memory to interconnected markdown with [[wikilinks]]
# Clone
git clone https://github.com/jaminitachi/SuperClaw.git ~/superclaw
cd ~/superclaw
# One-command setup
npm run setup
# Launch Claude Code — SuperClaw loads automatically
claude
The setup wizard handles everything:
┌─────────────────────────────────┐
│ Claude Code Session │
│ │
│ ┌────────────────────────────┐ │
│ │ 9 Lifecycle Hooks │ │
│ │ keyword-detector (prompt) │ │
│ │ session-start / session-end│ │
│ │ pre-tool / post-tool │ │
│ │ subagent-tracker │ │
│ │ persistent (Sisyphus) │ │
│ │ pre-compact │ │
│ └────────────────────────────┘ │
│ │
│ ┌────────────────────────────┐ │
│ │ 10 Team Agents │ │
│ │ Dev: dev-architect, │ │
│ │ dev-backend, dev-frontend,│ │
│ │ dev-qa │ │
│ │ Research: research-reviewer,│ │
│ │ research-writer, │ │
│ │ research-assistant │ │
│ │ Infra: infra-monitor, │ │
│ │ infra-mac │ │
│ │ Verify: verify │ │
│ └────────────────────────────┘ │
└──────────┬───────────────────────┘
│ MCP (stdio)
┌───────────────┼───────────────┐
│ │ │
┌──────┴──────┐ ┌─────┴──────┐ ┌──────┴──────┐
│ sc-bridge │ │ sc-peekaboo│ │ sc-memory │
│ 8 tools │ │ 15 tools │ │ 13 tools │
│ │ │ │ │ │
│ Telegram │ │ Screenshot │ │ SQLite+FTS5 │
│ Cron sched. │ │ UI inspect │ │ Persistent │
│ Status │ │ Click/type │ │ memory │
│ Routing │ │ App mgmt │ │ Obsidian │
└──────┬──────┘ │ AppleScript│ │ sync │
│ │ OCR │ │ Learnings │
┌─────────┴─┐ └─────┬──────┘ │ Verification│
│ Telegram │ │ └─────────────┘
│ Bot API │ ┌─────┴──────┐
└────────────┘ │ Peekaboo │
│ (Homebrew) │
└────────────┘
User: "이 버그 고쳐줘" (Fix this bug)
1. UserPromptSubmit hook detects "고쳐" + "버그" → Debug Team
2. Team composition injected:
- dev-backend (sonnet): Root cause analysis
- dev-architect (opus): Architecture context
- dev-qa (sonnet): Reproduce & verify
3. Agents execute in parallel
4. Stop hook blocks exit until work complete (Sisyphus)
5. Results verified independently before reporting
| Tool | Description |
|---|---|
sc_send_message | Send Telegram message |
sc_telegram_inbox | Get recent incoming messages |
sc_telegram_status | Bot connection status |
sc_route_command | Internal command router |
sc_status | System-wide health check |
sc_cron_list | List scheduled jobs |
sc_cron_add | Add cron job (5-field expression) |
sc_cron_remove | Remove cron job by name |
npx claudepluginhub jaminitachi/superclaw --plugin superclawCron-like daemon that runs Claude prompts on a schedule
OpenClaw AI assistant integration. Chat, manage sessions, access memory, and run async tasks through your OpenClaw instance.
A plugin for scheduling automated Claude Code tasks — cross-platform (macOS, Linux, Windows) recurring and one-off execution of skills, prompts, and scripts with safety controls and notifications
Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.
Curated Claude Code skills and commands for prompt engineering, MCP servers, subagents, hooks, and productivity workflows
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses