Full feature development pipeline: planner -> FE+BE parallel -> reviewer -> QA
npx claudepluginhub justn-hyeok/harness-for-yall --plugin dev-pipelineImplements backend APIs (Node/Express/FastAPI) based on dev-planner specs. Handles endpoint design, database schemas, business logic, validation, error handling. Use ONLY for quick backend work within a dev pipeline. For serious backend systems prefer be-* agents instead.
Implements React/Next.js/TypeScript UI based on dev-planner specs. Component design, state management, data fetching, responsive layouts. Use ONLY for quick frontend work within a dev pipeline. For React-specific work prefer fe-* agents instead.
Analyzes feature requirements, breaks them into frontend/backend tasks, defines acceptance criteria in Given/When/Then format, writes handoff specs. Use at the start of any new feature development. Triggers: plan feature, feature breakdown, requirements analysis, 기능 기획, 요구사항 분석.
Generates unit and integration tests, analyzes edge cases for implementations that have been reviewed. Blocks if dev-reviewer has not approved. Use at the end of a dev pipeline.
Reviews implementations from dev-frontend and dev-backend for correctness, style, security, cross-cutting concerns. Produces APPROVE or REQUEST_CHANGES verdict. Must run before dev-qa. For standalone multi-stage code review prefer review-* agents instead.
Multi-agent harness for Claude Code: 26 agents, 15 skills, 5 teams.
A pre-configured set of Claude Code agents organized into 5 specialized teams. Each team uses a different multi-agent orchestration pattern optimized for its purpose.
| Plugin | Pattern | Agents | Skills | What it does |
|---|---|---|---|---|
dev-pipeline | Pipeline | 5 | 1 | Full feature dev: planner → FE+BE parallel → reviewer gate → QA |
review-pipeline | Fan-out / Fan-in | 5 | 1 | Code review: 3 parallel screeners → moderator → judge (SARIF output) |
fe-experts | Expert Pool | 5 | 5 | Frontend: architect → implementer / styler → perf + tester |
be-experts | Pipeline + Expert Pool | 7 | 5 | Backend: architect → impl + validator → resilience / provider / security → tester |
explore-team | Hierarchical Delegation | 4 | 3 | Codebase exploration: scout(opus) → hypothesizer → evidence → synthesizer |
# All plugins
npx harness-for-yall
# Pick specific teams
npx harness-for-yall fe-experts be-experts
# Preview first
npx harness-for-yall --dry-run
# Overwrite existing
npx harness-for-yall --force
Copies agents/skills to ~/.claude/. Zero dependencies.
Inside Claude Code:
/plugin marketplace add justn-hyeok/harness-for-yall
Then install what you need:
/plugin install dev-pipeline@justn-harness
/plugin install review-pipeline@justn-harness
/plugin install fe-experts@justn-harness
/plugin install be-experts@justn-harness
/plugin install explore-team@justn-harness
git clone https://github.com/justn-hyeok/harness-for-yall.git
cd harness-for-yall
chmod +x install.sh && ./install.sh
┌─────────────┐
│ User Task │
└──────┬──────┘
│
┌────────────┼────────────┐
▼ ▼ ▼
┌──────────┐ ┌──────────┐ ┌──────────┐
│ Specific │ │ Generic │ │ Analysis │
│ fe / be │ │ dev │ │ explore │
└────┬─────┘ └────┬─────┘ └────┬─────┘
│ │ │
▼ ▼ ▼
┌──────────────────────────────────────┐
│ review-pipeline │
│ screener×3 → moderator → judge │
└──────────────────────────────────────┘
fe-* / be-* over dev-* when the task is clearly frontend or backendexplore → dev → review for complex workflows| Agent | Model | Why |
|---|---|---|
explore-scout | opus | Orchestration quality matters for architecture analysis |
| Everything else | sonnet | Cost efficiency — sonnet handles implementation well |
.claude-plugin/
marketplace.json # Plugin Marketplace catalog
plugins/
dev-pipeline/ # 5 agents, 1 skill
.claude-plugin/plugin.json
agents/ # dev-planner, dev-frontend, dev-backend, dev-reviewer, dev-qa
skills/dev-feature/
review-pipeline/ # 5 agents, 1 skill
agents/ # review-screener-{1,2,3}, review-moderator, review-judge
skills/review-code/
fe-experts/ # 5 agents, 5 skills
agents/ # fe-architect, fe-implementer, fe-styler, fe-perf, fe-tester
skills/ # fe-component, fe-page, fe-refactor, fe-review, fe-test
be-experts/ # 7 agents, 5 skills
agents/ # be-architect, be-implementer, be-validator, be-resilience, be-provider, be-security, be-tester
skills/ # be-api, be-mcp-server, be-pipeline, be-llm-integration, be-observability
explore-team/ # 4 agents, 3 skills
agents/ # explore-scout, explore-hypothesizer, explore-evidence, explore-synthesizer
skills/ # explore-investigate, explore-quick, explore-hypothesis
bin/install.mjs # npx CLI
package.json # npm config
install.sh # Shell installer
uninstall.sh # Shell uninstaller
Each agent is a standalone .md file with YAML frontmatter. Edit freely:
---
name: fe-architect
description: "React/Next.js component architecture"
model: sonnet # change to opus if you want
tools:
- Read
- Glob
- Grep
---
Skills are in SKILL.md format inside named folders. Add your own by creating plugins/<team>/skills/<name>/SKILL.md.
MIT
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
AI-powered development tools for code review, research, design, and workflow automation.