avenger-initiative

by Matrix Zion (ProSkillsMD)

Encrypted GitHub backup and restore for any OpenClaw agent system. Creates branch-per-night backups with smart retention (7 daily, 8 weekly, 12 monthly branches). Backs up openclaw.json (AES-256 encrypted), agent memories, SOUL/IDENTITY files, cron jobs, and custom skills to a private GitHub vault. Triggers on phrases like "avenger backup", "backup system", "push to vault", "sync vault", "avenger restore", "restore from vault", "setup avenger", "avenger status", "avenger init", "configure backup", "set up backup". Also auto-runs after any critical config change.

3.7k安全与合规未扫描2026年3月23日

安装

claude skill add --url github.com/openclaw/skills/tree/main/skills/asif2bd/avenger-initiative

文档

🛡️ Avenger Initiative

Encrypted, branch-based GitHub backup and restore for any OpenClaw system.

When This Skill Triggers

  1. User says "setup avenger" / "configure backup" / "avenger init" → Run SETUP flow
  2. User says "avenger backup" / "backup system" / "push to vault" → Run BACKUP
  3. User says "restore from vault" / "avenger restore" → Run RESTORE flow
  4. User says "avenger status" / "vault status" → Show STATUS
  5. After any confirmed config change (gateway restart, config patch) → Run BACKUP silently

SETUP FLOW (Agent-Guided)

When setup is triggered, walk the user through it conversationally. Ask one question at a time.

Step 1 — Ask for the vault repo

"To set up Avenger Initiative, I need a private GitHub repo to use as your vault. Have you created one already? If so, share the URL (e.g. https://github.com/yourname/my-vault). If not, I can help you create one."

Step 2 — Handle the encryption key

"Your openclaw.json (which contains all API keys and bot tokens) will be encrypted with AES-256 before being pushed. Do you have an existing encryption key from a previous Avenger setup, or should I generate a new one?"

Step 3 — Run setup

bash
bash ~/.openclaw/workspace/skills/avenger-initiative/scripts/setup.sh \
  --repo <vault-url>

Step 4 — Show key and insist they save it

"⚠️ Your encryption key is below — save it NOW in 1Password, Bitwarden, or a secure note. Without this key, your backup cannot be decrypted."

Wait for user to confirm "saved" before proceeding.

Step 5 — Explain what will be backed up

  • 🔐 openclaw.json — encrypted (all API keys, bot tokens, agent configs)
  • 🧠 All memory logs and workspace files (SOUL, IDENTITY, MEMORY, TOOLS)
  • 👥 Per-agent files for all agents
  • 🔧 All custom skills
  • 📋 Cron job definitions

Retention policy:

  • Daily → 7 days
  • Weekly → 8 weeks (created every Sunday)
  • Monthly → 12 months (created 1st of each month)

Step 6 — Run first backup & install cron

bash
bash ~/.openclaw/workspace/skills/avenger-initiative/scripts/backup.sh

BACKUP

bash
bash ~/.openclaw/workspace/skills/avenger-initiative/scripts/backup.sh

Creates backup/daily/YYYY-MM-DD branch → merges to main → prunes per retention policy.
On Sundays: also creates backup/weekly/YYYY-WNN.
On 1st of month: also creates backup/monthly/YYYY-MM.


RESTORE

bash
bash ~/.openclaw/workspace/skills/avenger-initiative/scripts/restore.sh

Supports --branch backup/daily/YYYY-MM-DD to restore from a specific snapshot.
Shows vault manifest, asks for confirmation, decrypts and restores all files.

After restore: openclaw gateway restart


STATUS

Check ~/.openclaw/workspace/memory/avenger-backup.log for last backup. Show timestamp, branch, and vault URL.


File Locations

code
~/.openclaw/
├── credentials/
│   ├── avenger.key              ← Encryption key (NEVER commit)
│   └── avenger-config.json     ← Vault repo URL
└── workspace/skills/avenger-initiative/
    ├── SKILL.md
    ├── scripts/
    │   ├── backup.sh
    │   ├── restore.sh
    │   └── setup.sh
    └── references/
        └── security.md

Security Model

  • Vault repo should be private on GitHub
  • openclaw.json → AES-256-CBC encrypted (PBKDF2, 100k iterations)
  • All other files → plaintext (no secrets)
  • Key lives only on the machine and in the user's password manager

See references/security.md for threat model and key rotation.


More verified OpenClaw skills available at proskills.md

相关 Skills

安全专家

by alirezarezvani

Universal
热门

覆盖威胁建模、漏洞评估、安全架构设计、代码审计与渗透测试,内置 STRIDE、OWASP、加密模式和安全扫描流程,适合系统设计评审与上线前安全排查。

安全专家把威胁建模、漏洞分析到渗透测试串成一套流程,内置 STRIDE 与 OWASP 指南,做安全设计和排查更省心。

安全与合规
未扫描9.0k

安全运营

by alirezarezvani

Universal
热门

覆盖应用安全、漏洞管理与合规审计,支持代码/依赖扫描、CVE 评估、Secrets 检测和安全自动化,适合做安全基线落地、漏洞响应、审计检查与安全开发治理。

应用安全、漏洞管理和合规检查一套打通,还能自动化扫描与响应,帮团队更早发现并收敛风险。

安全与合规
未扫描9.0k

安全审计

by alirezarezvani

Universal
热门

安装前审计 Claude Code Skill 的代码执行、Prompt 注入和依赖供应链风险,支持本地目录或 Git 仓库扫描,输出 PASS/WARN/FAIL 结论及修复建议

把代码审查、漏洞扫描和合规检查串成一条线,帮团队更早发现风险,做安全治理更省心。

安全与合规
未扫描9.0k

相关 MCP 服务

搜索和分析 Sentry 错误报告,辅助调试。

把零散的 Sentry 错误报告变成可检索线索,帮你在海量报错里更快定位线上故障,排障调试明显省时。

安全与合规
616

为 AI agents 提供安全层:拦截 prompt injection、识别伪造 packages,并扫描漏洞风险。

给 AI Agent 补上关键安全层,能拦截 prompt 注入、识别伪造包并扫描漏洞风险,把防护前置更省心。

安全与合规
92

强化安全性的 NotebookLM MCP,集成 post-quantum encryption,提升数据防护能力。

安全与合规
47

评论