A robust state-machine framework that converts conversational promises into persistent, trackable, and auto-executing files.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install commitment-engine
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install commitment-engine using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Commitment Engine?
The Commitment Engine v2 is designed to overcome the limitations of short-term memory in LLMs. While traditional context windows lose information over time, this skill transforms intentions into a persistent file-based state machine. By leveraging Openclaw Skills, it ensures that every verbal commitment—whether it is a recurring report or a one-time follow-up—is treated as a system-level guarantee rather than a fallible memory.
At its core, the engine operates on the philosophy of converting will into state. By using a Write-Ahead Logging (WAL) protocol, the agent is forced to record a task in the Commitment Ledger before even responding to a user. This architecture guarantees that the agent's scheduled actions are decoupled from the active conversation context, allowing for reliable execution even after a heartbeat wake-up.
Commitment Engine Use Cases
- Automatically tracking daily or weekly recurring tasks without user reminders.
- Setting hard deadlines for implicit tasks (e.g., automatically assigning a 21:00 deadline for same-day requests).
- Managing outbound follow-up promises with 1-hour internal timers.
- Creating a verifiable audit trail of all agent commitments and their current execution status.
How Commitment Engine Works
- The agent identifies a time-sensitive task within the conversation flow.
- Before replying to the user, the agent writes the task to workspace/commitments.md following the WAL protocol.
- During every heartbeat cycle, the Openclaw Skills protocol prioritizes a scan of the commitment ledger.
- Tasks within 30 minutes of their trigger time move to a preparing state to generate outputs.
- Tasks within 10 minutes of a deadline receive maximum priority, interrupting other non-essential processes.
- The state machine updates from active to completed or overdue, with immediate notifications sent for any failures.
Commitment Engine Setup
To initialize the Commitment Engine, ensure your agent has access to the workspace directory and configure the initial ledger file. For recurring tasks, integrate with the cron system:
# Add a hard guarantee for a recurring commitment
openclaw cron add --name "daily-report-prep" --cron "50 17 * * 1-5" --message "Commitment Engine Trigger: C001. Read commitments.md and execute."
Ensure the agent follows the H12 hard rule: write to the ledger before confirming the task to the user.
Commitment Engine Data Schema & Taxonomy
The system maintains a Commitment Ledger in Markdown format with the following structure:
| Attribute | Description |
|---|---|
| ID | Unique identifier for the commitment |
| Content | Detailed description of the task |
| Type | Classification: recurring or one-time |
| Status | active, preparing, awaiting_confirm, executing, completed, failed, overdue, cancelled |
| Trigger Time | The target timestamp for execution |
| Next/Last Execution | Tracking for recurring logic |
All state changes are logged both in the ledger and the agent's daily memory file.
Commitment Engine Advanced Features
- WAL (Write-Ahead Logging) protocol ensuring no task is confirmed without being recorded.
- Dual-layer protection combining soft heartbeat checks with hard cron triggers via Openclaw Skills.
- Priority escalation logic that interrupts low-priority tasks when a commitment deadline is within 10 minutes.
- Automatic status machine that handles draft confirmation, execution retries, and overdue alerts.
SKILL.md
Loading
Related Openclaw Skills
XiaoHongShu Content Migration
An automated solution for scraping XiaoHongShu notes and cross-posting them to Facebook Meta Business Suite and WordPress via REST API.
QMD Plus
QMD Plus enhances local markdown search by using LLMs to expand simple queries into sophisticated lexical and semantic search variations.
Harness Evolve
A self-evolution engine that consumes research logs and performs system self-checks to optimize AI agent architectures automatically.
Harness Research
Harness Research is an automated intelligence engine that tracks, analyzes, and maps the latest AI agent research papers directly to your system's improvement goals.
Capability Radar
A specialized skill designed to detect, tag, and log AI capability gaps and rule conflicts to drive continuous architectural evolution.
Agent Harness Architect
A professional diagnostic skill designed to harden long-running AI agent architectures by implementing structured session bridges and verification protocols.
Featured*
