harness-design

harness-design is a skill for Claude Code from AnastasiyaW/codex-claude-code-config. It costs 180 tokens per session (2,552 once invoked), scanned A, original, MIT.

A design guide for building long-running applications with several AI agents working in planned stages. The pattern separates planning, generation, and evaluation, with checks such as automated tests and browser-based Playwright tests.

In plain words
What is it for?
Use it to design multi-agent harnesses for full-stack applications, multi-feature products, and work lasting several hours. It helps define sprint contracts, evaluation steps, and context management.
Why use it?
It helps manage larger projects that are too complex or lengthy for one agent to handle reliably. Clear roles, quality criteria, and proof of results make progress easier to verify.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; built for openclaw.

Part of the claude-code-config plugin — 57 skills, 8 agents shipped together

Good fit Use it to design multi-agent harnesses for full-stack applications, multi-feature products, and work lasting several hours. It helps define sprint contracts, evaluation steps, and context management.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anastasiyaw/codex-claude-code-config/harness-design
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add AnastasiyaW/codex-claude-code-config --skill harness-design
Clone the repo
git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config

Made for: Claude Code.

Or install claude-code-config, the plugin that ships this one along with the rest of its 57 skills, 8 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for harness-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/harness-design/github.svg)](https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/harness-design)
Your own site
<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/harness-design"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/harness-design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for harness-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/harness-design"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/harness-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,552 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
  • medium Excessive Agency · line 16
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00180 $0.02552
Opus 5 $0.00090 $0.01276
Sonnet 5 $0.00036 $0.00510
Haiku 4.5 $0.00018 $0.00255

Measured yesterday against content hash bc44a79e4c04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

harness-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/architecture/harness-design/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 Bounded work with direct evidence Work that needs durable state, resumes, or independent evaluation
Качество Baseline достаточно Нужен polish, originality, craft
Стоимость В рамках явного бюджета задачи Бюджет и stop condition фиксируются для этой задачи
Проверка Прямой task-appropriate proof Независимая проверка и runtime proof, если требуются контрактом

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)

  • Превращает запрос пользователя в детальную, проверяемую спецификацию
  • Сохраняет утверждённый scope, явные non-goals и существующие границы продукта
  • Не добавляет AI-фичи, миграции стека или новые deliverables без запроса пользователя либо подтверждённой причинной необходимости
  • НЕ over-specify реализацию — только what, не how
  • Если AI-фичи уже входят в утверждённый scope, вписывает их 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
  • Выбирает проверку по acceptance contract: unit/integration/runtime probe для сервисов, browser/UI проверку только для затронутого пользовательского пути
  • Откалиброван через few-shot примеры
  • Ловит то, что self-evaluation пропускает

Read the full file on GitHub · 241 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday Changed · -2 lines · +9 tokens per session bc44a79e4c04
  2. 9d ago First seen · 243 lines · 171 tokens per session scan A 93169dc6ba58

Subscribe to this mod's changes

harness-design is a skill published in the GitHub repository AnastasiyaW/codex-claude-code-config (149 stars, last pushed today), licensed MIT. It adds 180 tokens to every session and 2,552 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.