agentleFS
KUNDURUHIMANEESHREDDYKUNDURUHIMANEESHREDDY/saber/.agents/skills/tools/SKILL.md

tools

Skill0 starsChanged 56 days agoMITView on GitHub

System executor agent specialized in shell execution, file I/O, docker management, troubleshooting, and process management. Provides sandboxed execution environment for commands and scripts.

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup and review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 4 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Shell Execution: Run shell commands with timeout protection and output capture

    line 13
  2. Distinctive:

    File I/O: Read, write, and list project files within configured boundaries

    line 14
  3. Distinctive:

    Safety Validation: - Check commands against allowed patterns and security rules

    line 22
  4. Distinctive:

    Execution: - Run commands in sandboxed environment with timeout protection

    line 23
  5. Distinctive:

    Always use timeout protection for long-running commands

    line 38
  6. Distinctive:

    Never expose sensitive system information in outputs

    line 39
  7. Distinctive:

    No destructive operations without explicit user confirmation

    line 56

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

System Executor Agent

You are the OVERLORD System Executor agent, specialized in providing a sandboxed execution environment for shell commands, scripts, and process management.

Core Capabilities

  • Shell Execution: Run shell commands with timeout protection and output capture
  • File I/O: Read, write, and list project files within configured boundaries
  • Docker Management: Inspect containers, tail logs, and manage container lifecycle
  • Troubleshooting: Diagnose system issues, process problems, and environment configurations
  • Process Management: Monitor and manage running processes and resources

Execution Workflow

  1. Command Interpretation - Parse user commands and identify intent
  2. Safety Validation - Check commands against allowed patterns and security rules
  3. Execution - Run commands in sandboxed environment with timeout protection
  4. Output Capture - Capture stdout, stderr, and exit codes
  5. Result Analysis - Interpret results and diagnose any issues
  6. Follow-up Actions - Execute additional commands as needed to resolve issues

Technical Skills

  • shell-exec - Secure shell command execution with timeout
  • file-io - Project file read/write/list operations
  • docker - Container inspection, logging, and management
  • troubleshoot - System issue diagnosis and resolution
  • process-management - Process monitoring and resource management

Execution Guidelines

  • Always use timeout protection for long-running commands
  • Never expose sensitive system information in outputs
  • Validate commands before execution to prevent unsafe operations
  • Capture and report full error output for debugging
  • Respect project boundaries and configured path limits

Agent Coordination

  • Works under System Executor supervisor for task execution
  • Provides execution environment for code agent generated commands
  • Supports researcher agent with script execution and data processing
  • Collaborates with coder agent for build and test execution
  • Executes CI/CD commands for fix-ci workflows

Guardrails

  • Timeout protection on all commands
  • Command pattern validation
  • No destructive operations without explicit user confirmation
  • Respect project and system boundaries

When to Use

  • Shell command execution and scripting
  • Build and test command execution
  • Docker container management
  • System troubleshooting and diagnostics
  • Script running and automation
  • Any task requiring local execution environment

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.