원클릭으로
speckit-memorylint-load-agents
Spec-kit workflow command: speckit-memorylint-load-agents
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Spec-kit workflow command: speckit-memorylint-load-agents
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
Think before building. Use when the user asks to reason about, analyze, evaluate, compare options, make an architecture decision, choose between approaches, think through a problem, or assess trade-offs. Also use when the user asks 'why did we...', 'should we...', 'what are our options', 'is this the right approach', or wants to frame/reframe a problem.
Archive a feature specification into main project memory after merge, resolving gaps and conflicts
Generate spec-kit configuration tailored to the existing codebase
Incrementally adopt SDD for existing features with reverse-engineered specs
Auto-discover project structure, tech stack, frameworks, and architecture patterns
Verify bootstrap output matches actual project structure and conventions
| name | speckit-memorylint-load-agents |
| description | Spec-kit workflow command: speckit-memorylint-load-agents |
| compatibility | Requires spec-kit project structure with .specify/ directory |
| metadata | {"author":"github-spec-kit","source":"memorylint:commands/load-agents.md"} |
$ARGUMENTS
You are the Core Rule Enforcer for the current workspace.
Your task is to load the AGENTS.md file from the workspace root directory into your context before the planning phase begins. This file contains the core infrastructure guidelines, system instructions, and safety protocols for AI agents. Your goal is to ensure that the upcoming planning (generation of plan.md and tasks.md) strictly adheres to these rules and prevents any drift from the established core constraints.
AGENTS.md: Read the contents of the AGENTS.md file located at the root of the workspace.AGENTS.md is missing, unreadable, or cannot be loaded from the workspace root for any reason, STOP immediately. Do not begin planning, do not generate or update plan.md or tasks.md, and do not continue to any subsequent step. Output a clear error stating that the mandatory before_plan gate failed because AGENTS.md could not be loaded, along with remediation guidance to restore the file, fix its readability or permissions, or correct the workspace root before retrying.AGENTS.md and explicitly state that these rules will be strictly followed and enforced during the subsequent planning and implementation steps.AGENTS.md or any other files during this operation. This is strictly a context-loading action to guarantee rule adherence.If AGENTS.md is loaded successfully, output a brief confirmation message indicating that AGENTS.md has been successfully loaded and that its rules will be enforced. For example:
AGENTS.md loaded successfully. Core rules and constraints have been established for the planning phase.
If AGENTS.md cannot be loaded, output a clear failure message and stop. For example:
ERROR: Mandatory before_plan gate failed: could not load AGENTS.md from the workspace root. Planning cannot proceed. Remediation: ensure AGENTS.md exists, is readable, and that the workspace root is correct, then retry.