Skip to content
Agentmart
Submit a tool

os-terminal-automation

Universal Terminal & Process Execution Playbook: Controlled shell execution, process monitoring, background task supervision, and operator safety gating.

Skill by alakbarr

IndexedMIT
Write a review

Chalk Labs

Need help deploying os-terminal-automation?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/alakbarr-os-terminal-automation

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Universal Terminal & Process Execution Playbook: Controlled shell execution, process monitoring, background task supervision, and operator safety gating.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/os-terminal-automation

What's inside

Skill name
os-terminal-automation
Description
Universal Terminal & Process Execution Playbook: Controlled shell execution, process monitoring, background task supervision, and operator safety gating.
License
MIT
Instructions
44 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# OS Terminal Automation & Process Supervision Playbook

## 1. Overview & Operational Principles
Enables Monika to execute command-line diagnostics, software maintenance, and background tasks safely within the host environment (Windows PowerShell / CMD / Bash).

Safety Fortress Axiom:
- **Read-Only Non-Destructive Commands**: Allowed directly for rapid diagnostics (e.g. `git status`, `git log`, `tasklist`, `uptime`, `dir`, `ps`, `cat`, `date`, `whoami`).
- **Mutating & System Operations**: Strictly intercepted into a `PendingAction("execute_terminal_command")` requiring explicit operator confirmation via Telegram inline button before shell execution.

## 2. Terminal Engine Architecture
Implemented in `analysis/tools/terminal_process_engine.py` and exposed via `analysis/tools/domain/terminal_tools.py`:
- **Foreground Execution**: Runs short commands with a strict timeout (default 60s, max 600s).
- **Automatic Demotion**: Commands exceeding foreground threshold or flagged with `background=True` are demoted to background process sessions with an assigned `session_id`.
- **Output Ring Buffer**: Retains stdout and stderr in rolling memory buffers for inspection via `process_manage(action='log', session_id=...)`.

## 3. Tool Usage Specifications

### Running Commands via `terminal`
```json
{
  "command": "git status --short",
  "timeout": 30.0,
  "background": false
}
```

### Supervising Background Tasks via `process_manage`
- **List Active Tasks**:
  `process_manage(action="list")`
- **Poll Status**:
  `process_manage(action="poll", session_id="sess_xyz")`
- **Read Streaming Logs**:
  `process_manage(action="log", session_id="sess_xyz", offset=0, limit=5000)`
- **Kill Process**:
  `process_manage(action="kill", session_id="sess_xyz")`

## 4. Safety Guardrails & Prohibited Commands
The following operations must never be executed without explicit operator proposal:
1. Deleting files or directories (`rm`, `del`, `Remove-Item`).
2. Force killing processes without operator review (`taskkill /F`, `kill -9`).
3. Modifying environment or system configurations (`setx`, registry modifications).
4. Git force push or reset discarding local workspace code.

From alakbarr/Monika, MIT.

More from alakbarr/Monika

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 12, 2026 (18 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from alakbarr

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get os-terminal-automation running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying os-terminal-automation?

CallGet help
Cite this page

os-terminal-automation skill. Agent Mart. https://agentmart.dev/skills/alakbarr-os-terminal-automation (last updated 2026-10-24)