Soul Guardian
技能 已验证 活跃Drift detection + baseline integrity guard for agent workspace files with automatic alerting support
To protect the integrity of agent workspace files from unauthorized changes, ensuring baseline fidelity and providing an auditable trail of modifications.
功能
- Detects unauthorized file changes against baselines
- Automatically restores critical files ('restore' mode)
- Provides alert-only notifications for other file types ('alert' mode)
- Maintains a tamper-evident audit log with hash chaining
- Supports custom policies for file monitoring
- Offers integration with scheduling tools (cron, launchd)
使用场景
- Use when you need to ensure agent configuration files (SOUL.md, AGENTS.md) are not modified without authorization.
- Use to automatically revert accidental or malicious changes to critical workspace files.
- Use to maintain a historical, tamper-evident record of all file changes within the agent workspace.
- Use to integrate workspace integrity checks into automated agent heartbeats or cron jobs.
非目标
- Not intended as a replacement for full version control systems like Git.
- Does not provide identity verification for who made the change (actor is best-effort metadata).
- Cannot protect against attackers who control both the workspace and the guardian's state directory.
- Does not automatically integrate with external alerting systems beyond basic console output or file logging.
安装
npx skills add prompt-security/clawsec通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
Audit Dependency Versions
100Audit project dependencies for version staleness, security vulnerabilities, and compatibility issues. Covers lock file analysis, upgrade path planning, and breaking change assessment. Use before a release to ensure dependencies are current and secure, during periodic maintenance reviews, after receiving a security advisory, when upgrading to a new language version, before submitting to CRAN or npm, or when inheriting a project to assess its dependency health.
Codex Diff Develop
100Revisa el diff de la rama actual frente a develop en proyectos Drupal 11 siguiendo la metodología Codex (lógica de negocio, edge cases de hooks/queries, seguridad, performance, completitud). Genera un informe .md en la carpeta del IDE detectado (.antigravity/, .cursor/, .vscode/ o docs/) con hallazgos por severidad y soluciones accionables. Usar cuando el usuario pida "Revisión diff develop", "revisión diff develop", "diff develop", "revisar diff", "codex diff" o expresiones similares con intención de auditar cambios contra develop. Triggers: diff develop, codex diff, revisión diff, lint diff develop, auditar diff.
Investigate Capa Root Cause
100Investigate root causes and manage CAPAs (Corrective and Preventive Actions) for compliance deviations. Covers investigation method selection (5-Why, fishbone, fault tree), structured root cause analysis, corrective vs preventive action design, effectiveness verification, and trend analysis. Use when an audit finding requires a CAPA, when a deviation or incident occurs in a validated system, when a regulatory observation needs a formal response, when a data integrity anomaly requires investigation, or when recurring issues suggest a systemic root cause.
Toprank Weekly Review
100Run a weekly SEO review for one registered website, write audit artifacts, and choose the next best safe action.
Janitor Tokens
100显示每个技能消耗的上下文窗口令牌数量。当用户询问有关令牌成本、上下文预算、技能大小，或希望了解哪些技能浪费了最多的上下文空间时使用。
Janitor Report
100一个完整的报告，用于检查所有技能的健康状况。当用户想要检查错误、查找重复项、检测损坏的技能或获取技能健康状况的完整概览时使用。