url: "https://docs.openclaw.ai/concepts/system-prompt" title: "System prompt - OpenClaw"

Search...

Ctrl K

Search...

Navigation

On this page

System Prompt

OpenClaw builds a custom system prompt for every agent run. The prompt is OpenClaw-owned and does not use the p-coding-agent default prompt.The prompt is assembled by OpenClaw and injected into each agent run.

Structure

The prompt is intentionally compact and uses fixed sections:

Tooling: current tool list + short descriptions.
Skills (when available): tells the model how to load skill instructions on demand.
OpenClaw Self-Update: how to run
```
config.apply
```
and
```
update.run
```
.
Workspace: working directory (
```
agents.defaults.workspace
```
).
Documentation: local path to OpenClaw docs (repo or npm package) and when to read them.
Workspace Files (injected): indicates bootstrap files are included below.
Sandbox (when enabled): indicates sandboxed runtime, sandbox paths, and whether elevated exec is available.
Current Date & Time: user-local time, timezone, and time format.
Reply Tags: optional reply tag syntax for supported providers.
Heartbeats: heartbeat prompt and ack behavior.
Runtime: host, OS, node, model, repo root (when detected), thinking level (one line).
Reasoning: current visibility level + /reasoning toggle hint.

Prompt modes

OpenClaw can render smaller system prompts for sub-agents. The runtime sets a

promptMode

for each run (not a user-facing config):

```
full
```
(default): includes all sections above.
```
minimal
```
: used for sub-agents; omits Skills, Memory Recall, OpenClaw Self-Update, Model Aliases, User Identity, Reply Tags, Messaging, Silent Replies, and Heartbeats. Tooling, Workspace, Sandbox, Current Date & Time (when known), Runtime, and injected context stay available.
```
none
```
: returns only the base identity line.

When

promptMode=minimal

, extra injected prompts are labeled Subagent Context instead of Group Chat Context.

Workspace bootstrap injection

Bootstrap files are trimmed and appended under Project Context so the model sees identity and profile context without needing explicit reads:

```
AGENTS.md
```
```
SOUL.md
```
```
TOOLS.md
```
```
IDENTITY.md
```
```
USER.md
```
```
HEARTBEAT.md
```
```
BOOTSTRAP.md
```
(only on brand-new workspaces)

Large files are truncated with a marker. The max per-file size is controlled by

agents.defaults.bootstrapMaxChars

(default: 20000). Missing files inject a short missing-file marker.Internal hooks can intercept this step via

agent:bootstrap

to mutate or replace the injected bootstrap files (for example swapping

SOUL.md

for an alternate persona).To inspect how much each injected file contributes (raw vs injected, truncation, plus tool schema overhead), use

/context list

/context detail

. See Context.

Time handling

The system prompt includes a dedicated Current Date & Time section when the user timezone is known. To keep the prompt cache-stable, it now only includes the time zone (no dynamic clock or time format).Use

session_status

when the agent needs the current time; the status card includes a timestamp line.Configure with:

```
agents.defaults.userTimezone
```
```
agents.defaults.timeFormat
```
(
```
auto
```
|
```
12
```
|
```
24
```
)

See Date & Time for full behavior details.

Skills

When eligible skills exist, OpenClaw injects a compact available skills list (

formatSkillsForPrompt

) that includes the file path for each skill. The prompt instructs the model to use

read

to load the SKILL.md at the listed location (workspace, managed, or bundled). If no skills are eligible, the Skills section is omitted.

Copy

<available_skills>
  <skill>
    <name>...</name>
    <description>...</description>
    <location>...</location>
  </skill>
</available_skills>

This keeps the base prompt small while still enabling targeted skill usage.

Documentation

When available, the system prompt includes a Documentation section that points to the local OpenClaw docs directory (either

docs/

in the repo workspace or the bundled npm package docs) and also notes the public mirror, source repo, community Discord, and ClawHub ( https://clawhub.com) for skills discovery. The prompt instructs the model to consult local docs first for OpenClaw behavior, commands, configuration, or architecture, and to run

openclaw status

itself when possible (asking the user only when it lacks access).

Agent loop Context

Ctrl+I

Assistant

Responses are generated using AI and may contain mistakes.

url: "https://docs.openclaw.ai/concepts/system-prompt" title: "System prompt - OpenClaw"

OpenClaw home page

Search...

Ctrl K

Search...

Navigation

On this page

System Prompt

Structure

The prompt is intentionally compact and uses fixed sections:

Tooling: current tool list + short descriptions.
Skills (when available): tells the model how to load skill instructions on demand.
OpenClaw Self-Update: how to run
```
config.apply
```
and
```
update.run
```
.
Workspace: working directory (
```
agents.defaults.workspace
```
).
Documentation: local path to OpenClaw docs (repo or npm package) and when to read them.
Workspace Files (injected): indicates bootstrap files are included below.
Sandbox (when enabled): indicates sandboxed runtime, sandbox paths, and whether elevated exec is available.
Current Date & Time: user-local time, timezone, and time format.
Reply Tags: optional reply tag syntax for supported providers.
Heartbeats: heartbeat prompt and ack behavior.
Runtime: host, OS, node, model, repo root (when detected), thinking level (one line).
Reasoning: current visibility level + /reasoning toggle hint.

Prompt modes

OpenClaw can render smaller system prompts for sub-agents. The runtime sets a

promptMode

for each run (not a user-facing config):

```
full
```
(default): includes all sections above.
```
minimal
```
: used for sub-agents; omits Skills, Memory Recall, OpenClaw Self-Update, Model Aliases, User Identity, Reply Tags, Messaging, Silent Replies, and Heartbeats. Tooling, Workspace, Sandbox, Current Date & Time (when known), Runtime, and injected context stay available.
```
none
```
: returns only the base identity line.

When

promptMode=minimal

, extra injected prompts are labeled Subagent Context instead of Group Chat Context.

Workspace bootstrap injection

Bootstrap files are trimmed and appended under Project Context so the model sees identity and profile context without needing explicit reads:

```
AGENTS.md
```
```
SOUL.md
```
```
TOOLS.md
```
```
IDENTITY.md
```
```
USER.md
```
```
HEARTBEAT.md
```
```
BOOTSTRAP.md
```
(only on brand-new workspaces)

Large files are truncated with a marker. The max per-file size is controlled by

agents.defaults.bootstrapMaxChars

(default: 20000). Missing files inject a short missing-file marker.Internal hooks can intercept this step via

agent:bootstrap

to mutate or replace the injected bootstrap files (for example swapping

SOUL.md

for an alternate persona).To inspect how much each injected file contributes (raw vs injected, truncation, plus tool schema overhead), use

/context list

/context detail

. See Context.

Time handling

session_status

when the agent needs the current time; the status card includes a timestamp line.Configure with:

```
agents.defaults.userTimezone
```
```
agents.defaults.timeFormat
```
(
```
auto
```
|
```
12
```
|
```
24
```
)

See Date & Time for full behavior details.

Skills

When eligible skills exist, OpenClaw injects a compact available skills list (

formatSkillsForPrompt

) that includes the file path for each skill. The prompt instructs the model to use

read

to load the SKILL.md at the listed location (workspace, managed, or bundled). If no skills are eligible, the Skills section is omitted.

Copy

<available_skills>
  <skill>
    <name>...</name>
    <description>...</description>
    <location>...</location>
  </skill>
</available_skills>

This keeps the base prompt small while still enabling targeted skill usage.

Documentation

When available, the system prompt includes a Documentation section that points to the local OpenClaw docs directory (either

docs/

openclaw status

itself when possible (asking the user only when it lacks access).

Agent loop Context

Ctrl+I

Assistant

Responses are generated using AI and may contain mistakes.

System prompt - OpenClaw

url: "https://docs.openclaw.ai/concepts/system-prompt" title: "System prompt - OpenClaw"

System Prompt

Structure

Prompt modes

Workspace bootstrap injection

Time handling

Skills

Documentation

Related Skills

English Translator and Improver

Bakery Merge Bounty Game Overview

VEO3 Video Generation Assistant System Prompt

url: "https://docs.openclaw.ai/concepts/system-prompt" title: "System prompt - OpenClaw"

System Prompt

Structure

Prompt modes

Workspace bootstrap injection

Time handling

Skills

Documentation

System prompt - OpenClaw

url: "https://docs.openclaw.ai/concepts/system-prompt" title: "System prompt - OpenClaw"

​ System Prompt

​ Structure

​ Prompt modes

​ Workspace bootstrap injection

​ Time handling

​ Skills

​ Documentation

Related Skills

English Translator and Improver

Bakery Merge Bounty Game Overview

VEO3 Video Generation Assistant System Prompt

url: "https://docs.openclaw.ai/concepts/system-prompt" title: "System prompt - OpenClaw"

​ System Prompt

​ Structure

​ Prompt modes

​ Workspace bootstrap injection

​ Time handling

​ Skills

​ Documentation

System Prompt

Structure

Prompt modes

Workspace bootstrap injection

Time handling

Skills

Documentation

System Prompt

Structure

Prompt modes

Workspace bootstrap injection

Time handling

Skills

Documentation