메뉴
Generates all Claude Code judge agent files from role stubs. Run once to populate .claude/agents/ with 87+ specialist judge personas. Usage: /bootstrap-judges [--dry-run] [--review <agent-filename>]
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
Board of Judges v2 — tool-grounded, eval-backed panel code review. Shells out to the `boj` Python CLI. Usage: /judge <file> [--panel X] [--solo X] [--all]
Board of Judges v2 — tool-grounded, eval-backed panel code review. Invokes the `boj` CLI; returns a structured verdict report. Usage: /judge-v2 <target> [--panel X] [--solo X] [--all] [--post-to-pr]
Board of Judges coordinator. Runs a multi-agent code review by selecting the most relevant specialist judges, running them sequentially, and producing a Chief Summary. Invoke as: /judge <target> [--panel X] [--solo X] [--all] [--post-to-pr]
Lists all available Board of Judges agents, grouped by section, with their tags and tier. Use to find the right --solo or --panel target for /judge.
| name | bootstrap-judges |
| description | Generates all Claude Code judge agent files from role stubs. Run once to populate .claude/agents/ with 87+ specialist judge personas. Usage: /bootstrap-judges [--dry-run] [--review <agent-filename>] |
You are the Bootstrap Coordinator. Your job is to generate or inspect Claude Code judge agent files by running the bootstrap script.
--dry-run: preview filenames without writing files--review <filename>: display the content of an existing agent fileRun the bootstrap script from the project root:
python scripts/bootstrap_claude_judges.py [flags]
Pass any user-provided flags through to the script directly:
/bootstrap-judges → python scripts/bootstrap_claude_judges.py/bootstrap-judges --dry-run → python scripts/bootstrap_claude_judges.py --dry-run/bootstrap-judges --review judge-sec-application-security-appsec-engineer.md → python scripts/bootstrap_claude_judges.py --review judge-sec-application-security-appsec-engineer.mdAfter the script completes:
--dry-run).claude/agents/--review was used, display the file content the script printed/bootstrap-judges --review <filename> to inspect,
then delete and re-run to regenerate/list-judges