openclaw-checkpoint
Backup and restore OpenClaw workspace state and agents across machines using git. Enables disaster recovery by syncing SOUL.md, MEMORY.md, memory files, cron jobs, agents (~/.openclaw/agents/), and configuration to a remote repository. Use when user wants to checkpoint their OpenClaw state, restore on a new machine, migrate between computers, or protect against data loss. Provides commands checkpoint (help overview), checkpoint-setup (interactive onboarding), checkpoint-backup, checkpoint-restore (with interactive checkpoint selection or --latest for most recent), checkpoint-schedule (auto-backup), checkpoint-stop, checkpoint-status, checkpoint-init, and checkpoint-reset. Supports multi-agent backup with flags --workspace-only, --agents-only, and --agent <name>. Automatically backs up cron jobs to memory/cron-jobs-backup.json on each checkpoint-backup.
What this skill does
# OpenClaw Checkpoint Skill
Backup and restore your OpenClaw identity, memory, agents, and configuration across machines.
**Platform:** macOS and Linux only. Windows is not supported.
## Overview
This skill provides disaster recovery for OpenClaw by syncing your workspace and agents to a git repository. It preserves:
- **Identity**: SOUL.md, IDENTITY.md, USER.md (who you and the assistant are)
- **Memory**: MEMORY.md and memory/*.md files (conversation history and context)
- **Cron Jobs**: Scheduled tasks exported to memory/cron-jobs-backup.json (morning briefs, daily syncs, automations)
- **Configuration**: TOOLS.md, AGENTS.md, HEARTBEAT.md (tool setups and conventions)
- **Scripts**: Custom tools and automation you've built
- **Agents**: All agent folders from ~/.openclaw/agents/ (alex, blake, etc.)
**Not synced** (security): API keys (.env.*), credentials, OAuth tokens
## Installation
### Option 1: Git Clone (Recommended)
```bash
# Clone the skill repo
git clone https://github.com/AnthonyFrancis/openclaw-checkpoint.git ~/.openclaw/skills/openclaw-checkpoint
# Copy scripts to tools directory
mkdir -p ~/.openclaw/workspace/tools
cp ~/.openclaw/skills/openclaw-checkpoint/scripts/checkpoint* ~/.openclaw/workspace/tools/
chmod +x ~/.openclaw/workspace/tools/checkpoint*
# Add to PATH (also add to ~/.zshrc or ~/.bashrc for persistence)
export PATH="${HOME}/.openclaw/workspace/tools:${PATH}"
# Run setup wizard
checkpoint-setup
```
### Option 2: Quick Install
```bash
curl -fsSL https://raw.githubusercontent.com/AnthonyFrancis/openclaw-checkpoint/main/scripts/install-openclaw-checkpoint.sh | bash
```
This runs the install script -- review it first if you prefer to inspect before executing.
## Commands
### checkpoint
**Show all available commands and usage examples.**
```bash
checkpoint
```
**What it does:**
- Displays a quick reference of all checkpoint commands with descriptions and examples
**When to use:**
- When you can't remember the exact command name
- Quick reference for available options
### checkpoint-setup
**Interactive onboarding flow for first-time setup.**
```bash
checkpoint-setup
```
**What it does:**
- Guides you through creating a PRIVATE GitHub repository
- Sets up SSH authentication (recommended) or Personal Access Token
- Automatically detects if SSH key is already authorized on GitHub
- Detects agents in `~/.openclaw/agents/` and reports they will be included in backups
- Generates a README.md with recovery instructions and commands
- Commits workspace files within `~/.openclaw/workspace` (secrets excluded via .gitignore)
- Configures automatic backups
- Tests the backup system
- Shows final status
**When to use:**
- First time setting up checkpoint system
- After installing the skill
- After running `checkpoint-reset`
- Recommended starting point for new users
### checkpoint-auth
**Authenticate with GitHub (browser-based).**
```bash
checkpoint-auth
```
**What it does:**
- Option 1: GitHub CLI (opens browser automatically)
- Option 2: Personal Access Token (expires, needs renewal)
- Option 3: SSH Key (recommended - no token expiry)
- Automatically adds GitHub to known_hosts
- Tests authentication after setup
**When to use:**
- Authentication expired or failed
- Switching authentication methods
- Setting up on a new machine
**SSH is recommended** because:
- No token expiration to worry about
- Works reliably without password prompts
- GitHub no longer accepts password authentication for HTTPS
### checkpoint-backup
Save current state to remote repository.
```bash
checkpoint-backup # Backup workspace + all agents
checkpoint-backup --workspace-only # Backup workspace only (skip agents)
checkpoint-backup --agents-only # Backup agents only (skip workspace/cron)
checkpoint-backup --agent alex # Backup only the 'alex' agent (+ workspace)
```
**What it does:**
- Backs up OpenClaw cron jobs to `memory/cron-jobs-backup.json` (requires `openclaw` CLI and running gateway)
- Copies agent folders from `~/.openclaw/agents/` into `agents/` in the workspace repo (strips nested `.git` dirs)
- Normalizes home-directory paths (`$HOME` -> `{{HOME}}`) for cross-machine portability
- Commits all changes in ~/.openclaw/workspace
- Pushes to origin/main
- Shows commit hash and timestamp
**Agent backup details:**
- Auto-detects agents in `~/.openclaw/agents/` (e.g., alex, blake)
- Each agent folder is copied to `agents/<name>/` in the backup repo
- Nested `.git` directories are removed to avoid submodule issues
- If no agents exist, skips gracefully with an info message
- Uses `rsync --exclude='.git'` when available, falls back to `cp -r` + manual `.git` removal
**Cron job backup details:**
- Runs `openclaw cron list --json` to export all scheduled tasks
- Strips runtime state, keeps only configuration (name, schedule, target, payload)
- Non-blocking: if the CLI or gateway is unavailable, checkpoint-backup continues without cron backup
**Flags:**
- `--workspace-only` — skip agent backup
- `--agents-only` — skip workspace and cron backup, only back up agents
- `--agent <name>` — back up a single named agent only
**When to use:**
- Before switching computers
- After significant changes (new memory, updated SOUL.md)
- Any time you want to ensure changes are saved
### checkpoint-schedule
Set up automatic backups with configurable frequency.
```bash
checkpoint-schedule 15min # Every 15 minutes
checkpoint-schedule 30min # Every 30 minutes
checkpoint-schedule hourly # Every hour (default)
checkpoint-schedule 2hours # Every 2 hours
checkpoint-schedule 4hours # Every 4 hours
checkpoint-schedule daily # Once per day at 9am
checkpoint-schedule disable # Turn off auto-backup
```
**What it does:**
- macOS: Creates launchd plist for reliable background backups
- Linux: Adds cron job for scheduled backups
- Logs all activity to ~/.openclaw/logs/checkpoint.log
**When to use:**
- First time setup: `checkpoint-schedule hourly`
- Change frequency: `checkpoint-schedule 15min`
- Stop backups: `checkpoint-schedule disable`
### checkpoint-status
Check backup health and status.
```bash
checkpoint-status
```
**What it shows:**
- Last backup time and commit
- Whether local is behind remote
- Uncommitted changes
- Agent backup status (which agents are backed up, which are missing)
- Auto-backup schedule status
- Recent backup activity log
**When to use:**
- Before switching machines (verify synced)
- Troubleshooting backup issues
- Regular health checks
### checkpoint-restore
Restore state from remote repository, with checkpoint selection and first-time onboarding.
```bash
checkpoint-restore # Select from recent checkpoints (interactive)
checkpoint-restore --latest # Restore most recent checkpoint (skip selection)
checkpoint-restore --force # Discard local changes before restoring
checkpoint-restore --workspace-only # Restore workspace only (skip agents)
checkpoint-restore --agents-only # Restore agents only (skip workspace/cron)
checkpoint-restore --agent alex # Restore only the 'alex' agent
```
**What it does:**
- **First-time users:** Launches interactive restore onboarding flow
- Guides you through GitHub authentication (SSH, GitHub CLI, or PAT)
- Lets you specify your existing backup repository
- Verifies access and restores your checkpoint
- Handles merge/replace options if local files exist
- Shows available checkpoints to pick from (if the repo has more than one commit)
- Offers to restore cron jobs from backup
- Offers to restore agents from backup
- **Returning users:** Shows a list of the 10 most recent checkpoints to choose from
- Pick the latest or any older checkpoint to restore
- Current checkpoint is marked in the list
- Restoring an older checkpoint warns that the next backup will overwrite newer remote checkpoints
- Use `--latest` flag to skip the interactive selection and restore theRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.