A command for running shell commands on the host computer, subject to configured permission rules. It returns command output and the exit code, which indicates whether the command succeeded.

Use it to list files, inspect project files, search directories, run Git commands, and execute other permitted terminal tasks in allowed directories.

It gives an agent a controlled way to inspect files, run development tools, and perform command-line work while restricting dangerous or unauthorized commands.

shell — Command for Claude Code by ankitaa186: A command for running shell commands on the host…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/ankitaa186/host-terminal-mcp/shell

Clone the repo

git clone --depth 1 https://github.com/ankitaa186/host-terminal-mcp

Made for: Claude Code.

Or install host-terminal, the plugin that ships this one along with the rest of its 2 skills, 5 commands, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/ankitaa186/host-terminal-mcp/shell.svg)](https://agentmods.dev/commands/ankitaa186/host-terminal-mcp/shell)

Your own site

<a href="https://agentmods.dev/commands/ankitaa186/host-terminal-mcp/shell"><img src="https://agentmods.dev/badge/commands/ankitaa186/host-terminal-mcp/shell.svg" alt="Measured on agentmods" height="20"></a>

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 347 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00010	$0.00347
Opus 5	$0.00005	$0.00173
Sonnet 5	$0.00002	$0.00069
Haiku 4.5	$0.00001	$0.00035

Measured 5d ago against content hash dca86795b74e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

shell scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Blocked commands**: Always rejected (e.g., `sudo`, `rm -rf /`)

commands/shell.md · 67 lines

What it actually says

Shell Command Execution

Execute terminal commands on the host machine with permission controls.

Workflow

Parse the command from user input
Check permissions against the configured allowlist
Execute if allowed, or request approval if in "ask" mode
Return results with stdout, stderr, and exit code

Usage

/shell <command>

Examples

List files

/shell ls -la ~/projects

Check git status

/shell git status

Search for files

/shell find . -name "*.js" -type f | head -20

View file contents

/shell cat package.json

Permission Handling

Commands are checked against the permission configuration:

Allowed commands: Execute immediately
Blocked commands: Always rejected (e.g., sudo, rm -rf /)
Unknown commands:
- In allowlist mode: Rejected
- In ask mode: Prompt for approval
- In allow_all mode: Execute (use with caution!)

Safety Notes

Commands run in the configured allowed directories only
Output is truncated if too large
Commands timeout after the configured limit
Dangerous commands are always blocked regardless of mode

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago First seen · 67 lines · 10 tokens per session scan C dca86795b74e

Subscribe to this mod's changes

shell is a command published in the GitHub repository ankitaa186/host-terminal-mcp (0 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 347 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

shell