메뉴
Inject VCP security and architecture standards into context. Run this at session start or after context compaction so the AI internalizes rules while writing code.
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
Build stage — per-unit implementation with fresh context and mechanical backpressure
PK Stage — multi-AI competitive debate with iterative consensus. Sends a topic to all configured AI participants simultaneously, synthesizes the best approach, then iterates until consensus or max rounds.
Code review stage — multi-AI semantic drift detection with AC tracing
Dev Buddy web configuration portal for managing presets and pipeline config
Decomposition stage — break features into small, independently testable units of work
Discovery stage — multi-AI codebase and running app exploration
| name | vcp-context |
| description | Inject VCP security and architecture standards into context. Run this at session start or after context compaction so the AI internalizes rules while writing code. |
| user-invocable | true |
| allowed-tools | Read, Glob, Bash |
| argument-hint |
This skill is a thin slash-command launcher. The authoritative workflow lives in the VCP MCP prompt vcp_context and resource vcp://prompts/vcp-context.
vcp_context with the caller-supplied host, current project path, and raw command arguments.get_prompt({ command: "vcp-context", host, project_path, arguments }) and follow the returned prompt text.detect_installation, validate_plugin_root, or resolve_config. Use those tools for deterministic work.Do not reimplement the workflow in this file; update the MCP prompt instead.