OpenClaw System Prompts

1. Course Content

Course Overview

• 💡 OpenClaw adopts an innovative "File-as-Prompt" architecture — the AI Agent's behavior, identity, memory, tool usage rules, etc., are all defined and loaded through multiple Markdown files in the Workspace.

2. 📂 Switching Workspaces

• OpenClaw's system prompts and skills are stored in the workspace path: $HOME/.openclaw/workspace
• The RDK X5 comes with preset Chinese and English workspace contents with identical meanings, differing only in language.
• Users in different regions can switch the language of the OpenClaw workspace documents according to their needs.
• Chinese Workspace (prompts and skills content are in Chinese)

cd /home/sunrise/language
sudo cp -a workspace-zh/. ~/.openclaw/workspace/
sudo chmod +x /home/sunrise/.openclaw/workspace/skills/sunrise-vision/scripts/*

• English Workspace (prompts and skills content are in English)

xxxxxxxxxx
cd /home/sunrise/language
sudo cp -a workspace-en/. ~/.openclaw/workspace/
sudo chmod +x /home/sunrise/.openclaw/workspace/skills/sunrise-vision/scripts/*

• After configuration, restart the OpenClaw gateway to apply the changes.

xxxxxxxxxx
openclaw gateway restart

[!WARNING]

• The hidden folders .workspace_en and .workspace_zh under the $HOME/.openclaw/workspace path are Chinese and English template files. It is recommended not to modify them.

3. AGENTS.md

• Function Description

AGENTS.md defines the top-level specifications for how the Agent operates within the workspace. 📖 It can be understood as the Agent's "User Manual" — telling the Agent how to start, how to manage memory, what it can do, and what it absolutely must not do.

• Content Structure

AGENTS.md mainly contains the following core sections:

[!NOTE]

⚠️ The factory-default AGENTS.md prompt restricts OpenClaw from modifying robot program code.

4. SOUL.md

• Function Description

SOUL.md is the Agent's "Soul" and Core 🧠. It defines the Agent's thinking style and behavioral guidelines when facing tasks — how to control the robot body, how to find and use skills, how to plan and execute actions, and when it should pause or refuse execution. SOUL.md shapes the Agent's core behavioral pattern as a "Robot Operator."

• Working Principle

SOUL.md is read by the Agent at the start of a session, serving as the underlying guiding principle for task execution. It does not specify specific skill parameters but rather dictates what thought process the Agent should use to handle any task. For example, the Agent is forced to check the skill library before starting any task and cannot execute directly based on feeling or memory — this habit of "checking documentation before acting" is defined by SOUL.md.

5. IDENTITY.md

• Function Description

IDENTITY.md defines the AI Agent's self-awareness and personality traits. It defines "who" the Agent is — its name, personality, language style, and basic identity positioning. This file gives the Agent a consistent personality when interacting with users.

• Working Principle

At the start of each session, the Agent reads IDENTITY.md to establish "self-awareness." This information affects the tone of the Agent's responses, the way it proactively offers help, and the style in which it builds relationships with users. For example, an Agent set to be "friendly and gentle" will naturally use more亲和 (approachable) language expressions when replying to users.

6. HEARTBEAT.md

• Function Description

HEARTBEAT.md is the configuration file that controls the heartbeat detection mechanism in OpenClaw ⏰. The heartbeat mechanism allows the Agent to periodically "wake up" to perform some background checks and maintenance tasks without active user-initiated sessions. This is similar to a robot's automatic periodic inspection — the Agent can silently complete memory organization, status checks, and other work in the background.

• Working Principle

The OpenClaw gateway regularly checks the content of the HEARTBEAT.md file to decide whether to trigger the Agent's heartbeat API call:

• File is empty or contains only comments: Skip the heartbeat call, and the Agent will not be woken up in the background.

[!NOTE]

💤 In the robot's factory configuration, the heartbeat mechanism is disabled by default.

7. 🛠️ TOOLS.md

• Function Description

TOOLS.md is the Agent's local notes for tool usage 📝. In the OpenClaw system, "Skills" define the general working methods of tools, while TOOLS.md records the Agent's own unique configurations and personalized settings. Simply put: Skills are the manual (general), and TOOLS.md are your personal notes (unique).

• Working Principle

During a session, the Agent reads both the relevant Skill documents to understand the general usage of tools and TOOLS.md to obtain unique configurations related to its deployment environment.

8. 👤 USER.md

• Function Description

USER.md is the exclusive file for the Agent to understand and remember user information. If IDENTITY.md is the window for the Agent to understand "who I am," then USER.md is the window for the Agent to understand "who you are dealing with." It records the user's basic information, preferences, project background, and other contextual information, helping the Agent provide more personalized and thoughtful service.

• Working Principle

At the start of each session, the Agent reads USER.md according to the process specified in AGENTS.md. Through this file, the Agent can:

• Know how to address the user (name, form of address)
• Understand the user's timezone, preferences, and other background information
• Remember things the user cares about and ongoing projects

9. 🧠 MEMORY.md

• Function Description

MEMORY.md is the AI Agent's long-term memory file 📚. In OpenClaw's memory system, there are two levels of memory storage:

1. 📓 Daily Records (memory/YYYY-MM-DD.md): Record raw events and conversation logs that happen each day, similar to a human's "diary."
2. 🗂️ Long-term Memory (MEMORY.md): Essence extracted from daily records, similar to a human's "long-term memory" — including important events, learned experiences, key decisions, and insights.

• Working Principle

The loading and use of MEMORY.md follow these rules:

• Loaded only in main sessions: When the user converses directly with the Agent, the Agent reads MEMORY.md to access long-term memory.
• Maintained autonomously by the Agent: The Agent can freely read, edit, and update MEMORY.md during main sessions.

[!NOTE]

In actual use, users can:

• ✏️ Actively write important information: Directly write content you think the Agent should remember long-term into MEMORY.md.
• 👀 Observe Agent's autonomous maintenance: After running the Agent for a while, check the content automatically accumulated in MEMORY.md.
• 🔄 Manage memory content: Regularly check and organize MEMORY.md, remove outdated information, and ensure long-term memory remains refined and accurate.