terminal
Local shell copilot for command planning, safe execution, preview-first workflows, output summarization, privacy-aware history controls, and step-by-step terminal help. Use whenever the user wants to run terminal commands, inspect files, debug shell issues, automate local tasks, or translate natural language into shell actions. Prefer safe preview before mutation. Require explicit confirmation for destructive commands. Local-only.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/agistack/terminalTerminal
Local shell copilot. Plan clearly, run carefully.
Core Philosophy
- Translate intent into executable shell steps.
- Prefer preview and inspection before mutation.
- Require explicit confirmation for destructive operations.
- Summarize results in human language after execution.
- Offer privacy-aware history controls for sensitive workflows.
Runtime Requirements
- Python 3 must be available as
python3 - Standard shell utilities should be available in the local environment
- No external packages required
Safety Model
- Local-only execution
- No external credential requests
- No hidden network activity
- Destructive operations require explicit confirmation
- Prefer read-only inspection first
- Blocked and previewed commands are recorded in local history
- Risk detection covers destructive, privilege-escalation, remote-fetch, and code-execution patterns
Privacy Controls
- History is stored locally only
- History file permissions are restricted to the local user when possible
- Use
--previewto inspect before execution - Use
--no-store-outputto avoid storing stdout/stderr in history for sensitive commands - Use
--redact-displayto mask sensitive-looking values in displayed output - Sensitive-looking tokens are redacted before history is written
Storage
All local data is stored only under:
~/.openclaw/workspace/memory/terminal/history.json
No cloud sync. No third-party APIs. No telemetry.
Workflows
- Plan command: Turn user intent into a safe shell command suggestion
- Preview risk: Explain command effects before execution
- Execute: Run a local command and capture stdout/stderr
- Summarize: Explain what happened in plain language
- History: Save executed, previewed, and blocked command runs locally
Scripts
| Script | Purpose |
|---|---|
init_storage.py | Initialize local terminal history storage |
plan_command.py | Generate a shell command from user intent |
run_command.py | Execute or preview a local command with safety checks and privacy controls |
summarize_result.py | Summarize command output in plain language |
show_history.py | Show recent command history |
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-agistack-terminal": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
Case
A comprehensive AI agent skill for anyone navigating a legal case. Whether you are the plaintiff, the defendant, or somewhere in between — this skill helps you understand what you are actually facing, build the strongest possible position, work with your attorney as an equal partner, make decisions at every fork in the road with clear eyes, and reach the best available outcome from wherever you are starting.
scraper
Structured extraction and cleanup for public, user-authorized web pages. Use when the user wants to collect, clean, summarize, or transform content from accessible pages into reusable text or data. Do not use to bypass logins, paywalls, captchas, robots restrictions, or access controls. Local-only output.
pitch-pro
Pitch development and presentation coaching for founders and salespeople. Use when user mentions investor pitches, sales presentations, elevator pitches, pitch decks, or persuasion scenarios. Builds value propositions, crafts pitches for different audiences, prepares for objections, and coaches delivery. All work is advisory - human judgment required for all decisions.
Daily Life Autopilot
The most comprehensive proactive life management skill for AI agents. Covers morning intelligence briefings, email and message triage, follow-up tracking, subscription and bill monitoring, file organization, meeting preparation, health habit nudges, and end-of-day review. Built for busy professionals, parents, entrepreneurs, and anyone who wants their AI to run the operational layer of daily life without being micromanaged. No technical setup required.
interview
Interview preparation system with company research, story building, and mock interview practice. Use when user mentions job interviews, interview prep, behavioral questions, salary negotiation, or follow-up messages. Researches companies, builds story libraries, runs mock interviews, prepares salary strategies, and drafts follow-ups. NEVER guarantees job offers.