By JunjaK
TypeScript-first multi-agent team workflow harness for Claude Opus 4.7 — 5 phases, TDD enforcement, escalation loops, worktree parallelization
Save or resume interrupted work via checkpoint files. Supports cross-session, cross-branch, and post-compaction recovery.
Team Brainstorm — Leader + Architects가 plan만 논의 (구현 없음, 시각화 포함)
Team Init — 프로젝트 구조 분석 및 프로필 생성/갱신
Team Workflow (Autonomous) — multi-agent team workflow with full auto-execution
Team Workflow (Interactive) — multi-agent team workflow with user involvement in planning
Backend architecture specialist — detailed backend/API plans for team workflow
Frontend architecture specialist — detailed frontend plans for team workflow
Infrastructure and security specialist — on-demand review for team workflow (Phase 1 + Phase 5)
TDD-based code developer — implements features following Red-Green-Refactor cycle in isolated worktrees
Team workflow leader — drafts plans, coordinates architects, manages approval gates and escalation
Save and restore work state across sessions, branches, and compactions. Use when saving progress before stopping, switching branches, or when the /checkpoint command is invoked.
Universal coding standards and best practices. Use in Phase 3 (Implementation) as the baseline for Designer agents. Covers readability, KISS, DRY, YAGNI, TypeScript patterns, error handling, and code smell detection.
Extract reusable patterns from sessions, manage session state, and evolve learnings into skills. Use at session end, after completing features, or when patterns emerge during work.
LSP-driven debugging patterns for TypeScript codebases. Complements the general debugging methodology in superpowers:systematic-debugging. Use in Phase 3-4 escalation scenarios or when investigating unexpected behavior.
Playwright E2E testing patterns. Use in Phase 4 (Verification) by Tester agents. Covers Page Object Model, test structure, configuration, flaky test strategies, artifact management, and CI/CD integration.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
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.
A reusable Claude Code harness for orchestrating multi-agent team workflows with 5 phases, escalation loops, and TDD enforcement.
This harness provides a structured team workflow where specialized AI agents collaborate through defined phases to implement features, fix bugs, or refactor code.
| Role | Agent | Model | When Called |
|---|---|---|---|
| Team Leader | team-leader | opus | Always (Phase 1, Gate, Escalation) |
| Architect A (Frontend) | team-architect-fe | opus | Phase 1 (parallel with B) |
| Architect B (Backend) | team-architect-be | opus | Phase 1 (parallel with A) |
| Architect C (Infra/Security) | team-architect-infra | opus | Phase 1 (on-demand) + Phase 5 (always) |
| UI/UX Master | team-uiux-master | sonnet | Phase 2 (conditional) |
| Designer x N | team-designer | opus | Phase 3 (parallel, worktree isolated) |
| Tester x N | team-tester | sonnet | Phase 4 (parallel) |
Phase 1: Planning
Leader drafts plan → Arch A + B detail (parallel) → Cross-review → File assignment
Phase 2: UI/UX (conditional)
UI/UX Master reviews and proposes changes
Leader Approval Gate
Approve → Phase 3 | Reject → Phase 1
Phase 3: Implementation (TDD)
Designer x N in parallel worktrees (Red-Green-Refactor)
Phase 4: Verification
Tester x N (unit + E2E, loop until pass)
Phase 5: Final Security Review
Arch C security & infra audit → SHIP or escalate
/team and /team-run report escalation events to user| Command | Description |
|---|---|
/team-init | Analyze project → generate profile (run first!) |
/team | Interactive mode — user participates in planning phase |
/team-run | Autonomous mode — full auto-execution |
/team-brainstorm | Planning only — Leader + Architects discuss, no implementation |
This harness is distributed as a Claude Code plugin.
# 1. Add the marketplace
/plugin marketplace add JunjaK/ai-harness
# 2. Install the plugin
/plugin install junjak-ai-harness@ai-harness
The plugin manifest cannot set environment variables or permissions. Add to your user or project settings.json:
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1",
"CLAUDE_AUTOCOMPACT_PCT_OVERRIDE": "60"
},
"permissions": {
"allow": [
"Edit",
"Write",
"LSP",
"Bash(git *)",
"Bash(ls *)",
"Bash(mkdir *)",
"Bash(bun *)",
"Bash(bunx *)",
"Bash(pnpm *)",
"Bash(npx *)"
]
}
}
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1is required —/team,/team-run,/team-brainstormdepend onTeamCreatefor cross-review.
This plugin depends on the impeccable skill for UI/UX work (shape, critique, audit, polish, etc.). impeccable is distributed as a single personal skill, not a Claude Code plugin — install it manually to:
~/.claude/skills/impeccable/
The impeccable agents (team-uiux-master, web-architect, web-reviewer) call it via Skill(skill="impeccable", args="<sub-command> [target]"). If the skill is missing they will abort with a request to install it.
/team-init # Scan project → generate .claude/project-profile/
/team "Add user authentication" # Start a workflow
/team-init generates .claude/project-profile/ in your project — all agents adapt to your stack and conventions.
The agents are framework-agnostic by default. To specialize for your project:
_docs/)Team plans are saved to the _docs/ directory with the following structure:
_docs/
├── index.md # Documentation index (always updated)
├── data-template/ # Category folder
├── data-sheet/ # Category folder
├── infra/ # Category folder
└── {category}/ # Add folders as needed
└── plan-{feature}.md # Team plan document
npx claudepluginhub junjak/ai-harness --plugin junjak-ai-harnessHarness-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
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques