Agent orchestration for Claude Code: 5 subprocess agents + 14 composable skills with cost-aware model tiering (fable/opus/sonnet/haiku), MCP-aware routing, and workflow fan-out. Agents spawn with fresh 200K context windows for true context isolation.
npx claudepluginhub aj-geddes/unicorn-teamAgent orchestration for Claude Code: 5 subprocess agents + 14 composable skills with cost-aware model tiering (fable/opus/sonnet/haiku), MCP-aware routing, and workflow fan-out. Agents spawn with fresh 200K context windows for true context isolation.
A Claude Code plugin that encodes the "hidden 80%" of software engineering expertise into 5 specialized agents and 13 composable skills.
Most AI coding tools help with the visible 20% -- writing code, answering syntax questions, generating boilerplate. But experienced developers spend 80% of their effort on skills that are rarely taught: reading code strategically, recognizing cross-domain patterns, estimating with risk awareness, self-reviewing before anyone sees the code, and managing technical debt deliberately.
This plugin encodes those skills into a coordinated agent team that Claude Code uses automatically.
# Add the marketplace
claude plugin marketplace add aj-geddes/unicorn-team
# Install the plugin
claude plugin install unicorn-team@unicorn-team
Done. Claude Code discovers all 13 skills, registers event hooks, and activates the orchestrator.
You make a request. The orchestrator analyzes it, routes to the right agent, and enforces quality gates on the result.
flowchart TB
User([User Request])
subgraph Orchestrator["ORCHESTRATOR"]
O["Analyze complexity\nSelect agent(s)\nEnforce quality gates"]
end
subgraph Agents["AGENT TEAM"]
direction LR
AR["Architect\nDesign + ADRs"]
DV["Developer\nTDD impl"]
QA["QA-Security\nReview + STRIDE"]
DO["DevOps\nCI/CD + infra"]
PG["Polyglot\nNew languages"]
end
subgraph Skills["SKILLS LIBRARY"]
direction LR
META["Meta Skills\nCode Reading | Patterns\nEstimation | Self-Review\nTech Debt | Learning"]
DOMAIN["Domain Skills\nPython | JavaScript\nTesting | Security\nDevOps"]
end
QG{{"Quality Gates\ntests pass · coverage ≥ 80%\nself-review complete"}}
User --> O
O --> AR & DV & QA & DO & PG
AR & DV & QA & DO & PG -.-> META & DOMAIN
AR & DV & QA & DO & PG --> QG
QG --> Result([Result + Proof])
style Orchestrator fill:#313244,stroke:#cba6f7,stroke-width:2px,color:#ffffff
style Agents fill:#313244,stroke:#fab387,stroke-width:2px,color:#ffffff
style Skills fill:#313244,stroke:#89b4fa,stroke-width:2px,color:#ffffff
style QG fill:#45475a,stroke:#a6e3a1,stroke-width:2px,color:#ffffff
Every implementation follows strict TDD:
flowchart LR
R["RED\nWrite failing test"]
G["GREEN\nMinimum code to pass"]
F["REFACTOR\nImprove, tests still green"]
V["VERIFY\nSelf-review + coverage"]
R --> G --> F --> V -->|Next feature| R
style R fill:#f38ba8,stroke:#f38ba8,color:#1e1e2e
style G fill:#a6e3a1,stroke:#a6e3a1,color:#1e1e2e
style F fill:#89b4fa,stroke:#89b4fa,color:#1e1e2e
style V fill:#cba6f7,stroke:#cba6f7,color:#1e1e2e
5 specialized agents with protocols inlined in their definitions (agents/*.md), keeping them off the slash command list:
| Agent | What It Does |
|---|---|
| architect | System design, ADRs, API contracts, tradeoff analysis |
| developer | TDD-first implementation across Python, JS/TS, Go, Rust |
| qa-security | 4-layer code review, STRIDE threat modeling |
| devops | CI/CD pipelines, deployment strategies, runbooks |
| polyglot | Rapid language acquisition, cross-ecosystem pattern transfer |
| Skill | What It Does |
|---|---|
| orchestrator | Routes tasks, delegates to agents, enforces quality gates |
| Skill | What It Does |
|---|---|
| self-verification | Systematic pre-commit quality checks (6-step protocol) |
| code-reading | Strategic codebase comprehension -- entry points, data flow, error paths |
| pattern-transfer | Recognize problem classes, transfer proven solutions across domains |
| estimation | Risk-aware PERT estimation with decomposition and confidence levels |
| technical-debt | Track, classify, and deliberately manage shortcuts and debt |
| language-learning | 5-phase protocol: zero to productive in a new language |
| Skill | Coverage |
|---|---|
| python | Type hints (3.10+), pytest, async, ruff, mypy, poetry |
| javascript | TypeScript, React, Node.js, Vitest, ESLint |
| testing | TDD protocol, mocking strategies, coverage, cross-language patterns |
| security | OWASP Top 10, STRIDE, input validation, secrets management |
| domain-devops | Docker, Kubernetes, GitHub Actions, observability stack |
Plus hvs-skill-buddy for skill library auditing and creation.
Claude Code marketplace entries for the plugin-safe Antigravity Awesome Skills library and its compatible editorial bundles.
Production-ready workflow orchestration with 84 marketplace plugins, 192 local specialized agents, and 156 local skills - optimized for granular installation and minimal token usage
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations