Agentic Harness Patterns

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.

311 stars 54 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add keli-wen/agentic-harness-patterns-skill --skill agentic-harness-patterns
Manual install
git clone --depth 1 https://github.com/keli-wen/agentic-harness-patterns-skill.git /tmp/agentic-harness-patterns-skill
mkdir -p ~/.claude/skills
cp -r /tmp/agentic-harness-patterns-skill/skills/agentic-harness-patterns ~/.claude/skills/agentic-harness-patterns

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Agentic Harness Patterns

Production AI coding agents are not just an LLM calling tools in a loop. The **harness** — memory, skills, safety, context control, delegation, and extensibility — is what separates a demo from a production system.

**For:** Engineers building or extending coding-agent runtimes, custom agents, or advanced multi-agent workflows.
**Not for:** Prompt engineering, model selection, generic software architecture, or LLM API basics.

All principles are distilled from production runtime decisions. Claude Code is used as grounding evidence, not as the only possible implementation.

## Choose Your Problem

| If you want to... | Read |
|---|---|
| Make the agent remember and improve over time | [Memory](#1-memory) |
| Package reusable workflows and expertise | [Skills](#2-skills) |
| Let the agent use tools powerfully but not dangerously | [Tools and Safety](#3-tools-and-safety) |
| Give the agent the right context at the right cost | [Context Engineering](#4-context-engineering) |
| Split work across multiple agents without losing control | [Multi-agent Coordination](#5-multi-agent-coordination) |
| Extend behavior with hooks, background tasks, or startup logic | [Lifecycle and Extensibility](#6-lifecycle-and-extensibility) |

**Before you start building:** Read the [Gotchas](#gotchas) — these are the non-obvious failure modes that cost the most time.

---

## 1. Memory

**User problem:** "My agent forgets corrections and project rules between sessions."
Read the full skill on GitHub

Details

Skill name
agentic-harness-patterns
Path
skills/agentic-harness-patterns/SKILL.md
License
MIT
Repo updated
2 April 2026

FAQ

What does the Agentic Harness Patterns skill do?

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.

How do I install the Agentic Harness Patterns skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add keli-wen/agentic-harness-patterns-skill --skill agentic-harness-patterns. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agentic Harness Patterns popular?

It lives in keli-wen/agentic-harness-patterns-skill, which has 311 GitHub stars and 54 forks.

Related skills

Agentic Harness Patterns Zh

311

keli-wen/agentic-harness-patterns-skill

AI Agent Harness 设计模式 — 记忆、权限、上下文工程、委派、技能、 Hook、Bootstrap。中文版。

AI, LLMs & Agents54

Wind MCP

896

jwangkun/claude-for-financial-services-cn

万得 Wind 金融数据 MCP 技能 — 44 个工具覆盖 A 股/港美股/基金/指数/债券/公告/宏观/分析 8 大服务域

AI, LLMs & Agents143

Generate Media

339

zhaihao118/Micro-Drama-Skills

短剧媒体生成技能。根据已生成的单部作品目录,调用 Google Gemini API(单一可配置图片模型生成角色图/分镜图),将生成的图片存放到对应各集目录下。支持视觉风格预设配置。关键词:图片生成、Gemini、Google API、分镜图片、角色参考图、media generation、视觉风格。

AI, LLMs & Agents87

User Alignment

508

tryproduck/produck-skills

Use when turning a vague or messy user request into an aligned, agent-executable PRD. Converts raw requests into testable specs with scope, phases, acceptance criteria, and explicit do-not-do boundaries for coding agents. Triggers on planning a feature from a rough ask, writing a PRD/spec, or aligning on intent before code.

AI, LLMs & Agents10

Migrate to Langfuse

342

langfuse/skills

Migrate to Langfuse from another LLM observability/evals platform (LangSmith, Arize AX, Phoenix, Braintrust, Helicone, Promptfoo, ...). A one-off vendor switch: live tracing cutover plus transfer of historical traces, datasets, prompts, and evaluators. Not for anything Langfuse-to-Langfuse — SDK or version upgrades, project/region moves, self-hosted to Cloud — and not for moving in-code prompts into Langfuse; the main langfuse skill covers those.

AI, LLMs & Agents46

Produck Feedback

508

tryproduck/produck-skills

Use when acting on real user feedback — you have a Produck feedback ticket or URL, or the user wants to fix something users complained about or build a feature users asked for. Pulls full feedback context through the Produck MCP and drives a feedback → aligned PRD → build loop. Triggers on "fix what users reported", a feedback ticket id, "use my produck feedback", or building from a feedback queue.

AI, LLMs & Agents10

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.