Skip to content
RemoteClaw

System Prompt

System Prompt

RemoteClaw builds a custom system prompt for every agent run. The prompt is RemoteClaw-owned and does not use the pi-coding-agent default prompt.

The prompt is assembled by RemoteClaw and injected into each agent run.

Structure

The prompt is intentionally compact and uses fixed sections:

  • Tooling: current tool list + short descriptions.
  • Safety: short guardrail reminder to avoid power-seeking behavior or bypassing oversight.
  • Skills (when available): tells the model how to load skill instructions on demand.
  • RemoteClaw Self-Update: how to run config.apply and update.run.
  • Workspace: working directory (agents.defaults.workspace).
  • Documentation: local path to RemoteClaw 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.

Safety guardrails in the system prompt are advisory. They guide model behavior but do not enforce policy. Use tool policy, exec approvals, sandboxing, and channel allowlists for hard enforcement; operators can disable these by design.

Prompt modes

RemoteClaw 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, RemoteClaw Self-Update, Model Aliases, User Identity, Reply Tags, Messaging, Silent Replies, and Heartbeats. Tooling, Safety, 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 context

The workspace is a plain working directory. Agents bring their own configuration (e.g. CLAUDE.md for Claude Code, .gemini/ for Gemini CLI). RemoteClaw does not inject workspace files into the context window — the agent CLI handles its own context loading.

Files that RemoteClaw may read or write in the workspace:

  • IDENTITY.md — agent name/vibe/emoji
  • HEARTBEAT.md — optional checklist for heartbeat runs
  • MEMORY.md and/or memory.md — long-term memory (when present)

To inspect how much each injected file contributes (raw vs injected, truncation, plus tool schema overhead), use /context list or /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, RemoteClaw 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.

<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 RemoteClaw docs directory (either docs/ in the repo workspace or the bundled npm package docs) and also notes the public mirror, source repo, and community Discord. The prompt instructs the model to consult local docs first for RemoteClaw behavior, commands, configuration, or architecture, and to run remoteclaw status itself when possible (asking the user only when it lacks access).