System prompt

System prompt 문서는 OpenClaw 공식 문서(concepts/system-prompt)를 한국어로 정리한 가이드입니다. What the OpenClaw system prompt contains and how it is assembled 명령·설정 키·코드 예시는 공식 문서를 그대로 보존하며, 해석과 절차 안내는 한국어로 제공합니다. 최종 동작은 설치된 CLI 버전과 공식 원문을 확인하세요.

핵심 요약

What the OpenClaw system prompt contains and how it is assembled

한국어 가이드 범위: concepts/system-prompt 경로의 설정·명령·제약·예시를 학습용으로 재구성합니다.

문서 구성

공식 문서의 주요 섹션은 다음과 같습니다.

Structure
Prompt modes
Prompt snapshots
Workspace bootstrap injection
Time handling
Skills
Documentation
관련 문서

상세 내용

본문

OpenClaw builds its own system prompt for every agent run; there is no runtime default prompt.

주요 항목:

buildAgentSystemPrompt renders the prompt from explicit inputs. It stays a pure renderer and does not read global config directly.
resolveAgentSystemPromptConfig resolves config-backed prompt knobs (owner display, TTS hints, model aliases, memory citation mode, sub-agent delegation mode) for a specific agent.
Runtime adapters (embedded, CLI, command/export previews, compaction) gather live facts (tools, sandbox state, channel capabilities, context files, provider prompt contributions) and call the configured prompt facade.
replace one of three named core sections: interaction_style, tool_call_style, execution_bias
inject a stable prefix above the prompt cache boundary
inject a dynamic suffix below the prompt cache boundary

Structure

The prompt is compact, with fixed sections:

주요 항목:

Tooling: structured-tool source-of-truth reminder plus runtime tool-use guidance. When the experimental update_plan tool is enabled (tools.experimental.planTool), its own tool description adds: use it only for non-trivial multi-step work, keep at most one step in_progress, and skip it for simple one-step work.
Execution Bias: act in-turn on actionable requests, continue until done or blocked, recover from weak tool results, check mutable state live, and verify before finalizing.
Safety: short guardrail reminder against power-seeking behavior or bypassing oversight.
Skills (when available): tells the model how to load skill instructions on demand.
OpenClaw Control: prefer the gateway tool for config/restart work; do not invent CLI commands.
OpenClaw Self-Update: inspect config safely with config.schema.lookup, patch with config.patch, replace the full config with config.apply, and run update.run only on explicit user request. The agent-facing gateway tool refuses to rewrite tools.exec.mode.
Workspace: working directory (agents.defaults.workspace).
Documentation: local docs/source path and when to read them.
Workspace Files (injected): notes that bootstrap files are included below.
Sandbox (when enabled): sandboxed runtime, sandbox paths, elevated-exec availability.
Current Date & Time: time zone only (cache-stable; the live clock comes from session_status).
Assistant Output Directives: compact attachment, voice-note, and reply-tag syntax.
Heartbeats: heartbeat prompt and ack behavior, when heartbeats are enabled for the default agent.
Runtime: host, OS, node, model, repo root (when detected), thinking level (one line).
Reasoning: current visibility level plus the /reasoning toggle hint.
use cron for future follow-up (check back later, reminders, recurring work) instead of exec sleep loops, yieldMs delay tricks, or repeated process polling
use exec / process only for commands that start now and continue in the background
when automatic completion wake is enabled, start the command once and rely on the push-based wake path
use process for logs, status, input, or intervention on a running command
for larger tasks, prefer sessions_spawn; sub-agent completion is push-based and auto-announces back to the requester
do not poll subagents list / sessions_list in a loop just to wait for completion

Prompt modes

OpenClaw renders smaller system prompts for sub-agents. The runtime sets a promptMode per run (not user-facing config):

주요 항목:

full (default): all sections above.
minimal: used for sub-agents; omits the memory prompt section (bundled as Memory Recall), OpenClaw Self-Update, Model Aliases, User Identity, Assistant Output Directives, Messaging, Silent Replies, and Heartbeats. Tooling, Safety, Skills (when supplied), Workspace, Sandbox, Current Date & Time (when known), Runtime, and injected context stay available.
none: returns only the base identity line.

Prompt snapshots

OpenClaw keeps committed prompt snapshots for the Codex runtime happy path under test/fixtures/agents/prompt-snapshots/codex-runtime-happy-path/. They render selected app-server thread/turn params plus a reconstructed model-bound prompt layer stack for Telegram direct, Discord group, and heartbeat turns: a pinned Codex gpt-5.5 model prompt fixture, the Codex happy-path permission developer text, OpenClaw developer instructions, turn-scoped collaboration-mode instructions when OpenClaw provides them, user turn input, and references to dynamic tool specs.

Workspace bootstrap injection

Bootstrap files are resolved from the active workspace and routed to the prompt surface matching their lifetime:

주요 항목:

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

Limit	Config key	Default
Per-file max characters	`agents.defaults.bootstrapMaxChars`	20000
Total across all files	`agents.defaults.bootstrapTotalMaxChars`	60000
Truncation warning (`off`\|`once`\|`always`)	`agents.defaults.bootstrapPromptTruncationWarning`	`always`

Time handling

The Current Date & Time section appears only when the user timezone is known, and only includes the time zone (no dynamic clock or time format) to keep the prompt cache-stable.

주요 항목:

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

Skills

When eligible skills exist, OpenClaw injects a compact list (`formatSkillsForPrompt`) with the **file path** and a content-derived `sha256:...` marker per skill. The prompt instructs the model to use `read` to load the SKILL.md at the listed location (workspace, managed, or bundled), and to re-read a skill when its differs from a previous turn. If no skills are eligible, the Skills section is omitted.

Scope	Skills prompt budget	Runtime excerpt budget
Global	`skills.limits.maxSkillsPromptChars`	`agents.defaults.contextLimits.*`
Per-agent	`agents.entries.*.skillsLimits.maxSkillsPromptChars`	`agents.entries..contextLimits.`

<available_skills>
  <skill>
    <name>...</name>
    <description>...</description>
    <location>...</location>
    <version>sha256:...</version>
  </skill>
</available_skills>

Documentation

The Documentation section points to local docs when available (docs/ in a Git checkout or the bundled npm package docs), falling back to https://docs.openclaw.ai otherwise. It also lists the OpenClaw source location: Git checkouts expose the local source root, package installs get the GitHub source URL with instructions to review source there when docs are incomplete or stale.

실습 체크리스트

공식 문서와 로컬 버전을 대조합니다: https://docs.openclaw.ai/concepts/system-prompt
관련 CLI는 openclaw --help 및 하위 명령 --help로 옵션을 확인합니다.
설정 변경 시 openclaw config / openclaw doctor로 유효성을 검사합니다.
Gateway·채널·플러그인 변경 후에는 필요 시 Gateway를 재시작합니다.

자주 쓰는 명령·설정 예시

<available_skills>
  <skill>
    <name>...</name>
    <description>...</description>
    <location>...</location>
    <version>sha256:...</version>
  </skill>
</available_skills>

System prompt

핵심 요약

What the OpenClaw system prompt contains and how it is assembled

한국어 가이드 범위: concepts/system-prompt 경로의 설정·명령·제약·예시를 학습용으로 재구성합니다.

문서 구성

공식 문서의 주요 섹션은 다음과 같습니다.

Structure
Prompt modes
Prompt snapshots
Workspace bootstrap injection
Time handling
Skills
Documentation
관련 문서

상세 내용

본문

OpenClaw builds its own system prompt for every agent run; there is no runtime default prompt.

주요 항목:

buildAgentSystemPrompt renders the prompt from explicit inputs. It stays a pure renderer and does not read global config directly.
resolveAgentSystemPromptConfig resolves config-backed prompt knobs (owner display, TTS hints, model aliases, memory citation mode, sub-agent delegation mode) for a specific agent.
Runtime adapters (embedded, CLI, command/export previews, compaction) gather live facts (tools, sandbox state, channel capabilities, context files, provider prompt contributions) and call the configured prompt facade.
replace one of three named core sections: interaction_style, tool_call_style, execution_bias
inject a stable prefix above the prompt cache boundary
inject a dynamic suffix below the prompt cache boundary

Structure

The prompt is compact, with fixed sections:

주요 항목:

Tooling: structured-tool source-of-truth reminder plus runtime tool-use guidance. When the experimental update_plan tool is enabled (tools.experimental.planTool), its own tool description adds: use it only for non-trivial multi-step work, keep at most one step in_progress, and skip it for simple one-step work.
Execution Bias: act in-turn on actionable requests, continue until done or blocked, recover from weak tool results, check mutable state live, and verify before finalizing.
Safety: short guardrail reminder against power-seeking behavior or bypassing oversight.
Skills (when available): tells the model how to load skill instructions on demand.
OpenClaw Control: prefer the gateway tool for config/restart work; do not invent CLI commands.
OpenClaw Self-Update: inspect config safely with config.schema.lookup, patch with config.patch, replace the full config with config.apply, and run update.run only on explicit user request. The agent-facing gateway tool refuses to rewrite tools.exec.mode.
Workspace: working directory (agents.defaults.workspace).
Documentation: local docs/source path and when to read them.
Workspace Files (injected): notes that bootstrap files are included below.
Sandbox (when enabled): sandboxed runtime, sandbox paths, elevated-exec availability.
Current Date & Time: time zone only (cache-stable; the live clock comes from session_status).
Assistant Output Directives: compact attachment, voice-note, and reply-tag syntax.
Heartbeats: heartbeat prompt and ack behavior, when heartbeats are enabled for the default agent.
Runtime: host, OS, node, model, repo root (when detected), thinking level (one line).
Reasoning: current visibility level plus the /reasoning toggle hint.
use cron for future follow-up (check back later, reminders, recurring work) instead of exec sleep loops, yieldMs delay tricks, or repeated process polling
use exec / process only for commands that start now and continue in the background
when automatic completion wake is enabled, start the command once and rely on the push-based wake path
use process for logs, status, input, or intervention on a running command
for larger tasks, prefer sessions_spawn; sub-agent completion is push-based and auto-announces back to the requester
do not poll subagents list / sessions_list in a loop just to wait for completion

Prompt modes

OpenClaw renders smaller system prompts for sub-agents. The runtime sets a promptMode per run (not user-facing config):

주요 항목:

full (default): all sections above.
minimal: used for sub-agents; omits the memory prompt section (bundled as Memory Recall), OpenClaw Self-Update, Model Aliases, User Identity, Assistant Output Directives, Messaging, Silent Replies, and Heartbeats. Tooling, Safety, Skills (when supplied), Workspace, Sandbox, Current Date & Time (when known), Runtime, and injected context stay available.
none: returns only the base identity line.

Prompt snapshots

Workspace bootstrap injection

Bootstrap files are resolved from the active workspace and routed to the prompt surface matching their lifetime:

주요 항목:

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

Limit	Config key	Default
Per-file max characters	`agents.defaults.bootstrapMaxChars`	20000
Total across all files	`agents.defaults.bootstrapTotalMaxChars`	60000
Truncation warning (`off`\|`once`\|`always`)	`agents.defaults.bootstrapPromptTruncationWarning`	`always`

Time handling

The Current Date & Time section appears only when the user timezone is known, and only includes the time zone (no dynamic clock or time format) to keep the prompt cache-stable.

주요 항목:

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

Skills

Scope	Skills prompt budget	Runtime excerpt budget
Global	`skills.limits.maxSkillsPromptChars`	`agents.defaults.contextLimits.*`
Per-agent	`agents.entries.*.skillsLimits.maxSkillsPromptChars`	`agents.entries..contextLimits.`

<available_skills>
  <skill>
    <name>...</name>
    <description>...</description>
    <location>...</location>
    <version>sha256:...</version>
  </skill>
</available_skills>

Documentation

실습 체크리스트

공식 문서와 로컬 버전을 대조합니다: https://docs.openclaw.ai/concepts/system-prompt
관련 CLI는 openclaw --help 및 하위 명령 --help로 옵션을 확인합니다.
설정 변경 시 openclaw config / openclaw doctor로 유효성을 검사합니다.
Gateway·채널·플러그인 변경 후에는 필요 시 Gateway를 재시작합니다.

자주 쓰는 명령·설정 예시

<available_skills>
  <skill>
    <name>...</name>
    <description>...</description>
    <location>...</location>
    <version>sha256:...</version>
  </skill>
</available_skills>

System prompt

핵심 요약

문서 구성

상세 내용

본문

Structure

Prompt modes

Prompt snapshots

Workspace bootstrap injection

Time handling

Skills

Documentation

관련 문서

실습 체크리스트

자주 쓰는 명령·설정 예시

관련 링크

관련 가이드

System prompt

핵심 요약

문서 구성

상세 내용

본문

Structure

Prompt modes

Prompt snapshots

Workspace bootstrap injection

Time handling

Skills

Documentation

관련 문서

실습 체크리스트

자주 쓰는 명령·설정 예시

관련 링크

관련 가이드