메뉴
Harness Engineering — how to build the integrated environment (CLAUDE.md/AGENTS.md, hooks, skills, commands, structured state) that makes AI agents work reliably across sessions. Load when the user asks about CLAUDE.md, AGENTS.md, hooks, harness design, or Claude Code project configuration from the AIASE course.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Agent architecture fundamentals — ReAct pattern, 4-element agent model, 5 sophistication levels, tool schema design, HITL risk matrix, 4-layer error handling, observability (traces/metrics/logs), framework selection, and deployment models. Load when the user asks about building agents, tool design, agent observability, ReAct, HITL, or agent frameworks.
Multi-agent patterns and team design — Orchestrator/Supervisor/Pipeline/Debate topologies, GAN-inspired Planner-Generator-Evaluator model, agent team coordination (Claude Code v2.1.32+), Skill vs. Sub-Agent decision framework, and the 4-layer agentic stack (L1 Skill → L2 MCP → L3 A2A → L4 CLI). Load when the user asks about multi-agent systems, agent teams, MCP, A2A protocol, or orchestration.
RAG (Retrieval-Augmented Generation) architecture — naive RAG pipeline, advanced techniques (HyDE, reranking, compression), modular RAG, GraphRAG, and practical debugging checklist. Load when the user asks about RAG, vector databases, embeddings, chunking, or retrieval systems from the AIASE course.
Spec-Driven Development (SDD) — how to write specs before coding with AI, the dimensional ascension/descent workflow, and dialogue-to-spec-to-code pipeline. Load when the user asks about writing specs, requirements, AIASE course SDD, or before starting any AI-assisted coding task.
AI era mental models and career strategy — three paradoxes (Agency/Depth/Automation), moat shift from features to data/domain, tacit vs. explicit knowledge, Automation vs. Augmentation career paths, labor market data, and career grid strategy. Load when the user asks about career decisions, how to position themselves in the AI era, competitive advantage, or the philosophical framing behind the AIASE course.
Research-Plan-Implement (RPI) workflow — the three-phase agentic SDLC for reliable AI-driven development, context window management, verifiability framework, and the autoresearch/gstack reference implementations. Load when the user asks about how to structure an AI coding session, how to plan before implementing, or the AIASE RPI framework.
| name | aiase-harness |
| description | Harness Engineering — how to build the integrated environment (CLAUDE.md/AGENTS.md, hooks, skills, commands, structured state) that makes AI agents work reliably across sessions. Load when the user asks about CLAUDE.md, AGENTS.md, hooks, harness design, or Claude Code project configuration from the AIASE course. |
From AIASE 2026 (NCKU), Week 5. The harness is the deterministic shell that wraps the probabilistic LLM core — it defines what cannot be negotiated, enforces rules the model cannot override, and maintains state across sessions.
"You cannot skip layers. Poor prompt engineering breaks context engineering; weak context engineering breaks harness engineering."
| Layer | Focus | Scope |
|---|---|---|
| Prompt Engineering | Craft single-prompt wording | Individual interactions |
| Context Engineering | Timing and format of information delivery | Session-level design |
| Harness Engineering | Integrated orchestration (commands, hooks, skills, agents) | Multi-session system architecture |
| Component | File/Path | Function |
|---|---|---|
| Context Management | claude-progress.txt, feature_list.json | Session continuity and state tracking |
| System Prompt | CLAUDE.md / AGENTS.md | Role definition + invariant rules |
| Lifecycle Hooks | settings.json | Event-driven control (pre/post-tool, stop, notification) |
| Sub-agents | .claude/agents/*.md | Role-specific agent definitions |
| Skills | .claude/skills/*/SKILL.md | Modular domain knowledge injection |
| Slash Commands | .claude/commands/ | Repeatable multi-step SOPs |
Also: init.sh — ensures clean environment setup across sessions.
# Project Overview
Objectives and scope.
# Tech Stack
Languages, frameworks, databases, ORMs.
# Architecture & Directory Structure
Layered design and file placement rules.
# Coding Conventions
Naming, async patterns, dependency injection, PascalCase, etc.
# Testing Protocols
Unit test structure, mocking rules, pre-commit validation.
# PR Guidelines
Commit message format, dependency direction checks.
Keep it under ~100 lines. Use it as a table of contents pointing to /docs subdirs. Oversized AGENTS.md causes context pollution and poor compliance.
init.sh ensures reproducibility| Layer | Content | Dependency Rule |
|---|---|---|
| Domain | Entities, Value Objects, Aggregates | No external deps |
| Application | DTOs, Use Cases, Validators | Orchestrates domain |
| Infrastructure | Database, Repository, External APIs | Implements data access |
| API | Controllers, Middleware | No business logic |
Dependency direction: API → Infrastructure → Application → Domain (unidirectional, enforced by lint).
"Every harness component encodes assumptions about model limitations. Prune scaffolding as models improve."
| Mistake | Impact | Fix |
|---|---|---|
| Oversized AGENTS.md | Context pollution | Keep ~100 lines; use as table of contents |
| Stale documentation | AI learns outdated rules | Automate doc maintenance via sub-agent |
| No reset mechanism | Context anxiety builds | Add intentional compaction triggers |
| Missing init.sh | Session start inconsistency | Codify clean-state boot sequence |
/docs: design-docs/, product-specs/, references/, SECURITY.mdfeature_list.json with pass/fail per featureinit.sh for clean environment reproductionclaude-progress.txt template with required fields/continue, /research, /review)security_check.mdSee also: [[aiase-sdd]] for spec writing, [[aiase-rpi]] for the research-plan-implement workflow, [[aiase-multi-agent]] for agent team design.