claude-code-harness-kit 是做什麼的？
一套 Claude Code 鉤子（唯讀自動批准、機密守衛、固執的 bash 守衛）加上 repo-radar，一個唯讀的倉庫分析技能。更少的提示摩擦，不減的安全性。
一套 Claude Code 鉤子（唯讀自動批准、機密守衛、固執的 bash 守衛）加上 repo-radar，一個唯讀的倉庫分析技能。更少的提示摩擦，不減的安全性。
xohzzwn6kcj9/claude-code-harness-kit 是一款專為 Claude Code 設計的輔助工具套件，旨在減少開發者與 AI 代理互動時的提示摩擦，同時維持甚至提升安全性。它內建多種鉤子功能：唯讀自動批准（read-only auto-approve）可自動允許安全、不修改內容的操作；機密守衛（secret guards）能防止 API 金鑰或令牌意外洩漏；固執的 bash 守衛（opinionated bash guards）則限制高風險的 shell 指令。此外，套件還包含 repo-radar，這是一個專門分析倉庫的唯讀技能，可獲取目錄結構、檔案摘要、相依性等資訊，而不需修改任何內容。此套件支援 Claude Code 平台，透過將常見的安全審查自動化，讓開發者能更專注於程式開發，無需手動批准每個讀取操作，從而提升工作效率。
npx skills add xohzzwn6kcj9/claude-code-harness-kitInstalled? Explore more 研究與資料分析 skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →
一套 Claude Code 鉤子（唯讀自動批准、機密守衛、固執的 bash 守衛）加上 repo-radar，一個唯讀的倉庫分析技能。更少的提示摩擦，不減的安全性。
USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.
Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.
Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Agent skill repository discovered by 10x-chat research.
Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `api/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.