Project Development
guanyang/open-agent-hub
This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token…
Design a scoped multi-agent harness for a requested long-running AI workflow.
Install Harness Design
$ npx skills add AnastasiyaW/codex-claude-code-config --skill harness-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AnastasiyaW/codex-claude-code-config harness-design --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/architecture/harness-design .claude/skills/harness-design && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "harness-design" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/architecture/harness-design into .claude/skills/harness-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-design", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/architecture/harness-designType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add AnastasiyaW/codex-claude-code-config --skill harness-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AnastasiyaW/codex-claude-code-config harness-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/architecture/harness-design .agents/skills/harness-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "harness-design" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/architecture/harness-design into .agents/skills/harness-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-design", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AnastasiyaW/codex-claude-code-config --skill harness-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AnastasiyaW/codex-claude-code-config harness-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/architecture/harness-design .cursor/skills/harness-design && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "harness-design" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/architecture/harness-design into .cursor/skills/harness-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-design", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/AnastasiyaW/codex-claude-code-config.git --path skills/architecture/harness-design--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add AnastasiyaW/codex-claude-code-config --skill harness-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AnastasiyaW/codex-claude-code-config harness-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/architecture/harness-design .gemini/skills/harness-design && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "harness-design" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/architecture/harness-design into .gemini/skills/harness-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-design", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install AnastasiyaW/codex-claude-code-config harness-designInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add AnastasiyaW/codex-claude-code-config --skill harness-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/architecture/harness-design .github/skills/harness-design && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "harness-design" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/architecture/harness-design into .github/skills/harness-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-design", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AnastasiyaW/codex-claude-code-config --skill harness-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AnastasiyaW/codex-claude-code-config harness-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/architecture/harness-design .opencode/skills/harness-design && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "harness-design" agent skill from https://github.com/AnastasiyaW/codex-claude-code-config/tree/main/skills/architecture/harness-design into .opencode/skills/harness-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-design", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
harness-design- GitHub stars
- 154
- Token cost
- ~2.6k tokens
- SKILL.md length
- 921 words
- Files
- 1
- Skills in repo
- 50
- Repo updated
- First seen
- Licence
- MIT
At a glance
Design a scoped multi-agent harness for a requested long-running AI workflow.
- Works in 3 steps: Planner (Планировщик) → Generator (Генератор) → Evaluator (Оценщик)
- : build a harness
- SKILL.md covers Когда нужен harness, а когда…, Архитектура: Three-Agent System, Sprint Contract Pattern and Generator-Evaluator: Почему…, plus 7 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Harness Design is an agent skill from AnastasiyaW/codex-claude-code-config. Design a scoped multi-agent harness for a requested long-running AI workflow. Preserve the user-approved product boundary while using Generator-Evaluator separation, testable sprint contracts, context management, and task-appropriate validation. 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"…
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Multi-agent orchestration, Load testing and Context engineering. It works with Claude Agent SDK. The repository describes itself as: Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development. The licence is MIT.
When your agent uses it
- : build a harness
- Multi-agent architecture
- Agent orchestration
- Generator-evaluator
Example prompts
- “build a harness”
- “multi-agent architecture”
- “agent orchestration”
- “/harness-design”
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 67709af. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Harness Design loads about 2.6k tokens when it runs. Until then it costs about 232 tokens; SKILL.md has 921 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from AnastasiyaW/codex-claude-code-config at commit 67709af, republished under its MIT licence (© AnastasiyaW). 921 words, ~2,558 tokens.
Download SKILL.mdSave it as
.claude/skills/harness-design/SKILL.md (or your agent's skills folder).- name
- harness-design
- description
- Design a scoped multi-agent harness for a requested long-running AI workflow. Preserve the user-approved product boundary while using Generator-Evaluator separation, testable sprint contracts, context management, and task-appropriate validation. 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).
- user-invocable
- true
- model
- opus
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
Sprint Contract Pattern
Перед каждой итерацией:
1. Planner определяет фичу и user story
2. Generator и Evaluator ДОГОВАРИВАЮТСЯ о:
- Что значит "done" для этой фичи
- Конкретные testable success criteria
- Что НЕ входит в scope
3. Generator реализует
4. Evaluator валидирует по контракту
5. Если конкретный критерий не пройден → конкретный feedback → повтор с п.3 только для этого критерияКонтракт = мост между user stories и implementation. Без него evaluator судит по своим критериям, generator не знает что проверять.
Останавливай цикл, когда все утверждённые criteria имеют требуемое доказательство. Не назначай число раундов заранее; продолжай только при наблюдаемом незакрытом критерии или новом опровергающем evidence.
Generator-Evaluator: Почему раздельно
Self-evaluation bias
Модели уверенно хвалят свою работу — даже когда качество посредственное. Это не баг модели, а свойство: генератор оптимизирован на producing, не на judging.
Решение: Independent evaluator
- Другой system prompt с calibrated skepticism
- Few-shot примеры с детальными score breakdowns
- Проверяет исполнимую поверхность acceptance contract: browser только для затронутого UI journey; native/API/worker задачи — их unit, integration, CLI или runtime probe, а не browser по умолчанию
- Конкретные failure criteria, а не общие "looks good"
Калибровка оценщика (QA Tuning Loop)
1. Evaluator выдаёт оценку
2. Ты проверяешь: согласен ли с оценкой?
3. Расхождение → обновляешь QA промпт
4. Типичные проблемы:
- Superficial testing, пропускает edge cases
- Premature approval посредственной работы
- Слишком строгие критерии → бесконечные итерации
5. Повторяешь пока evaluator judgment ≈ твой judgmentQuality Criteria Framework (для фронтенда)
4 измерения, каждое 0-10:
1. Design Quality — Целостность
Дизайн ощущается как единое целое, а не коллекция частей?
- Интеграция color, typography, layout, imagery
- Consistent visual language
2. Originality — Уникальность
Штраф за:
- Template layouts, library defaults
- AI slop patterns: purple gradients over white cards
- "Telltale signs of AI generation"
- Cookie-cutter структуры
3. Craft — Техническое мастерство
- Typography hierarchy
- Spacing consistency
- Color harmony, contrast ratios
- Pixel-perfect alignment
4. Functionality — Работоспособность
Пользователь завершает задачу без угадывания?
- Все интерактивные элементы работают
- Нет stub features
- Error states обработаны
Влияние формулировок на генерацию
Фразы в criteria прямо влияют на вывод генератора:
- "museum quality" → visual convergence к одному стилю
- "best designs" → перфекционизм за счёт creativity
- Тестируй формулировки — они стируют модель ДО оценки
Контекст-менеджмент
Context Degradation
Модели теряют coherence по мере заполнения context window.
Context reset > Compaction:
- Compaction сохраняет continuity, но не даёт чистый лист
- Reset + structured handoff artifact = лучший баланс
- Handoff artifact = документ с state, decisions, progress
Context Anxiety
Модели могут сворачивать работу раньше времени из-за роста контекста.
- Решение: clean context resets, когда они уменьшают риск потери важных ограничений
Structured Handoff
При context reset передавать:
- Что уже сделано (с конкретными файлами/строками)
- Какие решения приняты и почему
- Что осталось сделать
- Текущие проблемы и blockers
- Sprint contract для текущей итерацииAssumption Testing
"Every component in a harness encodes an assumption about what the model can't do on its own"
Show full SKILL.md (363 more words)Show less
Принцип: предположения устаревают
- Возможности моделей меняются, поэтому необходимость каждого harness-компонента должна подтверждаться наблюдаемым риском
- Стратегия: при наличии безопасного измеримого эксперимента убирать компоненты по одному, измерять влияние и откатывать ухудшение
Simplification Loop
1. Текущий harness работает? Да →
2. Убери один компонент (напр. sprint decomposition)
3. Качество упало? Да → верни. Нет →
4. Повтори с другим компонентом
5. Остановись на минимальном harness для текущей задачиРеальные failure modes (пойманные evaluator'ом)
- Rectangle fill tool ставит тайлы только на endpoints drag, вместо заполнения области
- Delete key handler требует два условия, когда нужно одно
- FastAPI route matching: "reorder" матчится как integer frame_id
- Audio recording: stub без mic capture
- Missing clip resize/split operations
- Effect visualizations как числовые слайдеры вместо графики
- Display-only features без интерактивности
- Missing instrument panels
- Unimplemented recording functionality
Инструментарий
Claude Agent SDK
- Handles agent orchestration + compaction автоматически
- Manages context growth across long sessions
- Рекомендуемый стек для production harnesses
Проверочные инструменты
- Для UI: browser automation и screenshots проверяют реальный затронутый user journey
- Для API, очередей и данных: contract/integration tests, health/runtime probes и проверка нужных persistent states
- Используй инструменты, уже поддержанные проектом; не меняй стек ради соответствия этой skill
Иллюстративные технологии
React/Vite, Nuxt/Vue, FastAPI/Fastify, SQLite/PostgreSQL и Playwright — примеры веб-проектов на момент написания, а не default, требование или инструкция к миграции. Выбирай технологии по существующей архитектуре, пользовательскому запросу и текущей документации.
Gotchas
- Language shapes output: формулировки в criteria сдвигают генератор ДО обратной связи от оценщика. "Museum quality" → convergence, "experimental" → divergence
- Не обосновывай продолжение цикла номером итерации: новая итерация нужна только при незакрытом criterion или новом evidence
- Cost/time figures are dated examples, not gates: если бюджет нужен, согласуй task-specific limit и не понижай acceptance ради формального PASS
- Evaluator may need tuning: меняй QA prompt только в ответ на конкретный false positive/negative и повторно проверяй затронутый criterion
- Self-evaluation is seductive: генератор БУДЕТ говорить "всё отлично" — не верь, проверяй через independent evaluator
Troubleshooting
| Симптом | Причина | Решение |
|---|---|---|
| Evaluator всё одобряет | Промпт слишком мягкий | Добавь few-shot с detailed score breakdowns, конкретные failure criteria |
| Generator не улучшается | Feedback слишком абстрактный | Evaluator должен давать конкретные файлы/строки/проблемы |
| Бесконечные итерации | Criteria невыполнимы или feedback не связан с ними | Пересмотри контракт; сохраняй требуемую safety/runtime планку, а несовместимый scope split только с явным решением пользователя |
| Context degradation | Длинная сессия без reset | Structured handoff + clean context reset |
| Все итерации выглядят одинаково | Criteria слишком узкие | Расширь пространство, убери "museum quality" формулировки |
| Evaluator ловит мелочи, пропускает крупное | Wrong priority в промпте | Restructure: critical → high → medium → cosmetic |
© AnastasiyaW, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/architecture/harness-design of AnastasiyaW/codex-claude-code-config.
Open the folder on GitHubat commit 67709af
Compare with similar skills
Harness Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Harness Design this skillAnastasiyaW/codex-claude-code-config | 154 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Project Developmentguanyang/open-agent-hub | 977 | 2 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Harness Engineering10xChengTu/harness-engineering | 102 | 1 repos | ~1k | Automated safety check: Pass | None | |
| Cozempic Session GuardRuya-AI/cozempic | 425 | — | ~434 | Automated safety check: Pass | MIT | |
| Filesystem Contextguanyang/open-agent-hub | 977 | 1 repos | ~4k | Automated safety check: Pass | MIT | |
| Durable Session StateZaxbyHub/opencode-swarm | 496 | — | ~896 | Automated safety check: Pass | MIT |
Similar skills
Harness Engineering
10xChengTu/harness-engineering
Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.
Cozempic Session Guard
Ruya-AI/cozempic
Starts a background daemon that watches a Claude Code session's size and prunes it before auto-compaction can discard context or agent-team state.
Filesystem Context
guanyang/open-agent-hub
This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem memory, or cleanup…
Durable Session State
ZaxbyHub/opencode-swarm
Keeps plans, decisions, evidence and reviewer verdicts in small files so long multi-phase tasks survive context compaction and session resumes.
OpenRig Mental Model Primer
mvschwarz/openrig
Gives a fast orientation to OpenRig for an agent that just booted into a seat, covering rigs, topologies, layers and where context and skills come from.
More from AnastasiyaW/codex-claude-code-config
All 50 skills in this repoBug Reproducer
AnastasiyaW/codex-claude-code-config
Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix.
Motion Framer
AnastasiyaW/codex-claude-code-config
A skill your agent uses when implementing Motion or Framer Motion in React/JavaScript: interactive UI components, micro-interactions, gestures, layout or page transitions, and scroll-based animation.
Proof Verify
AnastasiyaW/codex-claude-code-config
Plan-based verification - freeze acceptance criteria before building, then verify after with an independent fresh-context agent (the builder must not verify their own work).
Workflow Orchestration
AnastasiyaW/codex-claude-code-config
Написание и запуск Claude Code dynamic workflows (JS-оркестратор субагентов).
Notebooklm Grounded Research
AnastasiyaW/codex-claude-code-config
A skill your agent uses when: NotebookLM, notebooklm MCP, large documentation sets, courses, books, papers, or citation-backed research are mentioned.
Deepseek Provider Contract
AnastasiyaW/codex-claude-code-config
Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries.
Related
Works with
Categories
Questions about Harness Design
What does Harness Design do?
Design a scoped multi-agent harness for a requested long-running AI workflow. Harness Design is an agent skill from AnastasiyaW/codex-claude-code-config. Design a scoped multi-agent harness for a requested long-running AI workflow.
When should I use Harness Design?
Harness Design fits situations like: : build a harness; multi-agent architecture; agent orchestration; generator-evaluator.
How do I install Harness Design in Claude Code?
Run `npx skills add AnastasiyaW/codex-claude-code-config --skill harness-design -a claude-code`. Or copy the skill folder (skills/architecture/harness-design in AnastasiyaW/codex-claude-code-config) into .claude/skills/harness-design in your project. Claude Code loads it when a task matches its description.
How do I install Harness Design in Codex?
Run `npx skills add AnastasiyaW/codex-claude-code-config --skill harness-design -a codex`. Or copy the skill folder (skills/architecture/harness-design in AnastasiyaW/codex-claude-code-config) into .agents/skills/harness-design in your project. Codex loads it when a task matches its description.
Can I use Harness Design in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AnastasiyaW/codex-claude-code-config --skill harness-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harness-design, .gemini/skills/harness-design, .github/skills/harness-design and .opencode/skills/harness-design in your project.
What does Harness Design need to run?
SKILL.md names no scripts, command-line tools or credentials: Harness Design is instructions for the agent only.
Does Harness Design access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Harness Design safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Harness Design use?
Harness Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Harness Design use?
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Harness Design?
Skills that share tags, products or a category with Harness Design: Project Development (guanyang/open-agent-hub, 977 stars), Harness Engineering (10xChengTu/harness-engineering, 102 stars), Cozempic Session Guard (Ruya-AI/cozempic, 425 stars) and Filesystem Context (guanyang/open-agent-hub, 977 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Harness Design?
AnastasiyaW (a GitHub user) maintains it in AnastasiyaW/codex-claude-code-config, which has 154 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 9, 2026.
Source: AnastasiyaW/codex-claude-code-config on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.