Help us improve
Share bugs, ideas, or general feedback.
The Agent Harness for Claude Code — Guardrails, Observability, and Quality Gates for AI-Powered Development. 15 specialist agents with structured workflows, budget controls, analytics, and self-learning.
npx claudepluginhub seokan-jeong/team-shinchanThe Agent Harness for Claude Code — Guardrails, Observability, and Quality Gates for AI-Powered Development. 15 specialist agents with structured workflows, budget controls, analytics, and self-learning.
Claude Code marketplace entries for the plugin-safe Antigravity Awesome Skills library and its compatible editorial bundles.
Production-ready workflow orchestration with 83 marketplace plugins, 191 local specialized agents, and 155 local skills - optimized for granular installation and minimal token usage
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations
Share bugs, ideas, or general feedback.
Guardrails, Observability, Ontology, and Quality Gates for AI-Powered Development
15 specialist agents with structured workflows, project ontology, budget controls, analytics, and self-learning.
AI agents are powerful but unpredictable. Without constraints, they hallucinate architecture, skip reviews, blow through token budgets, and forget past decisions. An Agent Harness solves this by wrapping agents in guardrails, quality gates, and feedback loops -- the same way a test harness wraps code in assertions.
Team-Shinchan turns Claude Code into a harnessed multi-agent system where 15 specialists debate, plan, execute, and learn -- all within well-defined boundaries.
| Without a Harness | With Team-Shinchan |
|---|---|
| Agent starts blind, re-reads the whole codebase | Project Ontology auto-builds a knowledge graph on first session |
| Agents skip stages, jump to code | Workflow Guard enforces stage-tool matrix |
| No visibility into agent behavior | Analytics with trace IDs track every action |
| Unlimited token burn | Budget Guard caps spend per session |
| No quality signal on the harness itself | Harness Lint checks plugin integrity |
| Past decisions forgotten | Memory + Ontology + session bridging persist context |
| Code reviewed ad-hoc (or not at all) | Action Kamen reviews every phase (mandatory) |
Team-Shinchan is built on 5 Harness Engineering principles:
Load the right knowledge at the right time.
session-wrap and resume for cross-session continuityHard boundaries that prevent structural drift.
Automated checks that prevent bad outcomes.
Observability and continuous improvement.
src/analytics.js)src/harness-lint.js)src/gen-architecture-map.js generates agent hierarchy, workflow, invariant rules, and entry points; --check flag integrates into CIsrc/eval-schema.js, src/regression-detect.js)Durable state across sessions and workflows.