harness-design

Featured

Design and build multi-agent harness architectures for long-running AI application development. GAN-inspired Generator-Evaluator pattern, Sprint Contract negotiation, context management, quality criteria calibration. Based on Anthropic Engineering patterns. Use when: "build a harness", "multi-agent architecture", "agent orchestration", "generator-evaluator", "long-running app", "harness design", "agent pipeline", "quality evaluation loop", "sprint contract", "build app with agents", "Claude Agent SDK architecture", or when building complex full-stack apps that need planning → generation → evaluation cycles. Also use when discussing context degradation, self-evaluation bias, or assumption testing in AI workflows. Do NOT use to stress-test or critique an already-written plan document; use plan-swarm-review for that (this skill designs the harness, it does not review plans).

AI & Automation 138 stars 20 forks Updated 1 months ago MIT

Install

View on GitHub

Quality Score: 89/100

Stars 20%
71
Recency 20%
75
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Multi-Agent Harness Design Источники: - Anthropic Engineering — "Harness design for long-running apps" - OpenClaw-RL paper (arxiv 2603.10165) — personal agent verification - DenisSergeevitch/repo-task-proof-loop — execution protocol with durable proof См. также: `references/proof-loop-research.md` — детали paper + repo mapping ## Когда нужен harness, а когда хватит solo agent | Сигнал | Solo agent | Harness | |--------|-----------|---------| | Scope | Одна фича, bug fix, refactor | Full-stack app, multi-feature product | | Длительность | < 30 мин | 1-6+ часов | | Качество | Baseline достаточно | Нужен polish, originality, craft | | Стоимость | ~$5-15 | ~$100-200+ | | Проверка | Manual review | Automated evaluation + Playwright | **Правило:** Evaluator оправдан когда задача **за пределами reliable solo performance**. Не фиксированное yes/no — зависит от complexity tier. --- ## Архитектура: Three-Agent System ### 1. Planner (Планировщик) - Расширяет 1-4 предложения пользователя в **детальную спецификацию** - Амбициозный scope — находит возможности для AI-фич - **НЕ** over-specify реализацию — только what, не how - Вписывает AI features в продукт органично ### 2. Generator (Генератор) - Реализует фичи итеративно - Включает **self-evaluation** перед handoff (но она ненадёжна — см. ниже) - Работает в рамках Sprint Contract ### 3. Evaluator (Оценщик) - **Независимый** от генератора — отдельный контекст, отдельный промпт - Валидирует через Playwright MCP — скриншоты, нав...

Details

Author
AnastasiyaW
Repository
AnastasiyaW/claude-code-config
Created
5 months ago
Last Updated
1 months ago
Language
Python
License
MIT

Integrates with

Anthropic · AI Playwright · Testing

Bundled in these plugins

claude-code-config

Related Skills

AI & Automation Featured

code-simplifier

Review RTK Rust code for idiomatic simplification. Detects over-engineering, unnecessary allocations, verbose patterns. Applies Rust idioms without changing behavior.

79,919 Updated today
rtk-ai
AI & Automation Featured

design-patterns

Rust design patterns for RTK. Newtype, Builder, RAII, Trait Objects, State Machine. Applied to CLI filter modules. Use when designing new modules or refactoring existing ones.

79,919 Updated today
rtk-ai
AI & Automation Featured

issue-triage

Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.

79,919 Updated today
rtk-ai