exec-display
Structured command execution with security levels, color-coded output, and 4-line max summaries. Enforces transparency and visibility for all shell commands. Use when running any exec/shell commands to ensure consistent, auditable output.
Why use this skill?
Standardize your agent's command execution with exec-display. Get structured, audit-ready, and color-coded shell output with built-in security levels.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/globalcaos/exec-displayWhat This Skill Does
The exec-display skill serves as the foundational wrapper for all shell-based operations within the OpenClaw environment. Rather than allowing raw, opaque shell execution, this tool mandates a structured, transparent process for every command run by the agent. By requiring classification, clear purpose documentation, and condensed output summaries, it ensures that every interaction with the host system is auditable, secure, and visually consistent.
This utility categorizes commands into five distinct security levels (SAFE to CRITICAL), enabling the agent to communicate potential risks clearly. It uses ANSI color-coding to provide immediate visual feedback on the nature of the task being performed. By enforcing a 4-line maximum for output summaries, it prevents terminal clutter and ensures that the agent remains focused on high-level results rather than raw, verbose system logs.
Installation
To integrate this utility into your OpenClaw environment, use the standard hub installation command. This skill should ideally be installed early in your setup as it acts as a gatekeeper for subsequent task execution:
clawhub install openclaw/skills/skills/globalcaos/exec-display
Use Cases
This skill is essential whenever your agent needs to interact with the file system or environment settings. Common use cases include:
- Verifying repository states (git status, branch checks) as a SAFE activity.
- Modifying local project files, such as updating configuration files or adding environment variables as a LOW or MEDIUM activity.
- Managing system-level dependencies or service restarts. Note that for HIGH or CRITICAL level commands, the skill acts as a safety mechanism by prompting for manual intervention rather than proceeding with automated execution.
- Providing structured, human-readable logs of agent activity during debugging or complex automation tasks.
Example Prompts
- "Check the current status of the project directory and list all pending git changes using the exec-display wrapper."
- "Update the project configuration to point to the new staging environment and log the change via the exec-display script."
- "Attempt to restart the local Nginx web server; if it requires root privileges, show the command for me to run manually."
Tips & Limitations
- Mandatory Wrapper: The golden rule of this skill is that no raw shell commands should be executed directly. Always pipe through
cmd_display.py. - Output Summarization: Do not dump raw log files into the output. Use the summarization feature to extract only the success/fail indicator or the key result.
- Safety First: Treat HIGH and CRITICAL classifications seriously. If you aren't sure of the impact of a command, default to a more restrictive classification. The script is designed to protect your system from accidental changes.
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-globalcaos-exec-display": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
jarvis-voice
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
shell-security-ultimate
Classify every shell command as SAFE, WARN, or CRIT before your agent runs it.
memory-pioneer
Benchmark your agent's memory. Contribute anonymized scores to open research. Citizen science for AI memory.
subagent-overseer
Monitor sub-agent health and progress via a pull-based bash daemon. Use when spawning sub-agents that need progress tracking, staleness detection, and automatic status reporting. Replaces manual heartbeat polling with a deterministic status file the agent reads every 3 minutes. Zero AI tokens for monitoring — pure OS-level process checks and filesystem diffs.
model-router
Automatic LLM model selection for sub-agent tasks. Classifies tasks by complexity and type, then routes to the optimal model (cost vs capability). Use when spawning sub-agents, choosing models for cron jobs, or deciding which model to use for any task. Eliminates manual model specification by providing a decision tree and optional cheap-model classifier for ambiguous cases.