tycono
seongsu-kang/tyconoPlugin
AI team orchestration for Claude Code. Instead of one AI doing everything, Tycono gives you a team — CTO designs architecture, Engineer writes code, QA validates, Designer handles UI — all coordinating automatically while you watch in real-time. Key features: - Multi-agent collaboration: CEO supervises, dispatches tasks to specialized roles - Real-time observability: see what each team member is doing via activity stream - Domain agencies: install pre-built team configurations (gamedev, startup-mvp, solo-founder) - Custom agencies: create your own team with /tycono:agency-create (guided setup with auto-verification) - Knowledge persistence: AKB (Agentic Knowledge Base) accumulates insights across sessions - Tycono Channel: MCP-based real-time notifications pushed to your Claude Code session
Why this score
Popularity score: 56/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Nov 4, 2026 at commit 68724ac2a082, first 300 source files (it's a large repo), with Cisco's open-source skill-scanner.
What its code does:
- Runs shell commands Common for dev tools. Read the commands it runs.bin/auth-detect.ts:9, bin/cli.js:6, bin/tycono.ts:5 and 97 more
- Runs code it builds while running (eval or exec) Harder to read ahead of time, since the code is assembled while it runs.packages/server/src/api/src/engine/context-assembler.ts:883
- Makes network requestsscripts/validate-sse-stream.py:23, test-session-centric.py:21, test-sse-replay.py:21 and 15 more
- Downloads content and runs it Whatever it downloads can change after we scanned it.packages/plugin/scripts/version.sh:77
Web addresses in its code:
- tycono.aipackages/plugin/scripts/agency-create.sh:136
- raw.githubusercontent.compackages/server/src/api/src/routes/skills.ts:61
- api.tycono.aipackages/pixel/src/api/cloud.ts:3
- claude.aibin/tycono.ts:37
These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Nothing from another maker does quite the same job yet.