Markdown Editor

AI 코딩 에이전트 키트

코딩 어시스턴트와 에이전트의 안전한 도입: 에이전트 규칙 파일, 코딩 표준, 스킬과 MCP 서버, 정책과 도구 권한.

사용 순서에 따라 3단계로 정리한 템플릿 8개입니다. 편집기에서 템플릿을 열어 작성한 뒤 PDF, DOCX 또는 HTML로 내보낼 수 있습니다.

1단계

문제 정의

  1. AGENTS.md Template for AI Coding Agents

    표준

    Repository instructions for AI coding agents: setup, build and test commands, conventions, architecture map, PR and security rules

    AGENTS.md convention (agents.md)
  2. CLAUDE.md Project Memory Template

    표준

    Claude Code project memory: summary, commands, key paths, conventions, testing and workflow rules, gotchas, AGENTS.md import

  3. Cursor Project Rules Template (.mdc)

    경량

    Cursor .cursor/rules/*.mdc files: front matter fields, rule types, a complete example rule and rule ideas

  4. Coding Standards Template

    표준

    Team coding standards: naming, tool-enforced formatting, structure, errors, logging, tests, reviews, language rules

2단계

구축

  1. Agent Skill Specification Template (SKILL.md)

    전체

    Agent Skill spec: activation description, SKILL.md frontmatter, layout, scripts, progressive disclosure budget, versioning, security review, evals

    Agent Skills specification (agentskills.io, checked 2026-10-22)
  2. MCP Server Specification Template (Model Context Protocol)

    전체

    Transport, discovery, capabilities, tools, CacheableResult, MRTR confirmation and requestState, OAuth, OWASP 2026 mapping, errors, tests

    Model Context Protocol specification, revision 2026-07-28; OWASP Top 10 for LLM Applications 2026; OWASP Top 10 for Agentic Applications 2026
3단계

검토와 거버넌스

  1. AI Coding Assistant Policy Template

    전체

    Policy for AI coding assistants and agents: autonomy levels, tool register, secrets, sandboxing, review of generated code, provenance, OWASP ASI and SSDF mapping

    OWASP Top 10 for Agentic Applications 2026; NIST SP 800-218 SSDF 1.1; EU AI Act Art. 4
  2. Agent Tool and Permission Design Template (OWASP ASI02, ASI03)

    전체

    Agent tool permissions: tool inventory, capability classes, least agency, non-human identity, approval tiers, sandboxing, limits, audit, revocation, tests

    OWASP Top 10 for Agentic Applications 2026 (ASI02, ASI03); OWASP Top 10 for LLM Applications 2026 (LLM03 Excessive Agency)