A command for viewing and changing the rules that control which terminal commands may run. Its modes can allow only listed commands, ask before unknown commands, or allow all commands.

Use it to view permission settings, change the command policy, or approve a command for the current session.

It makes command execution rules visible and lets you approve specific commands or adjust the level of restriction.

permissions — Command for Claude Code by ankitaa186

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.

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/permissions/github.svg)](https://agentmods.dev/commands/ankitaa186/host-terminal-mcp/permissions)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/ankitaa186/host-terminal-mcp/permissions"><img src="https://agentmods.dev/badge/commands/ankitaa186/host-terminal-mcp/permissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 583 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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	$0.00008	$0.00583
Opus 5	$0.00004	$0.00292
Sonnet 5	$0.00002	$0.00117
Haiku 4.5	$0.00001	$0.00058

Measured 10d ago against content hash 1cdd24466985, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

permissions 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 10d 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 (like `sudo`, `rm -rf /`) are **always** blocked regardless of mode

commands/permissions.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Permission Management

View and manage terminal command permissions.

Workflow

Parse action from user input
Execute the appropriate permission tool
Display current status or confirm changes

Usage

/permissions status              # View current settings
/permissions mode <mode>         # Change permission mode
/permissions approve <command>   # Approve a specific command

Actions

View Status

/permissions status

Shows:

Current permission mode
Allowed directories
Number of allowed/blocked patterns
Session-approved commands

Change Mode

/permissions mode allowlist    # Only pre-approved commands (safest)
/permissions mode ask          # Prompt for unlisted commands
/permissions mode allow_all    # Allow everything (DANGEROUS!)

Approve Command

/permissions approve npm install

Approves a specific command for the current session (when in ask mode).

Permission Modes Explained

Mode	Behavior	Risk Level
`allowlist`	Only commands in the allow list can run	🟢 Safest
`ask`	Unknown commands prompt for approval	🟡 Moderate
`allow_all`	All commands execute without checks	🔴 Dangerous

Example Output

🔐 Terminal Permissions
━━━━━━━━━━━━━━━━━━━━━━

Mode:              allowlist
Allowed dirs:      ~, /tmp
Timeout:           300s
Max output:        100,000 chars

Patterns:
  ✅ Allowed:      73 patterns
  🚫 Blocked:      15 patterns

Session approved:
  - npm install
  - make build

Security Notes

allowlist is the default and recommended for production
ask mode approvals are session-only (not persisted)
allow_all should only be used in isolated/sandboxed environments
Blocked commands (like sudo, rm -rf /) are always blocked regardless of mode
Changes can optionally be persisted to config with persist: true

Configuration File

For permanent changes, edit ~/.config/host-terminal-mcp/config.yaml:

Read the full file on GitHub · 105 lines

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.

10d ago First seen · 105 lines · 8 tokens per session scan C 1cdd24466985

Subscribe to this mod's changes

permissions is a command published in the GitHub repository ankitaa186/host-terminal-mcp (0 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 8 tokens to every session and 583 once invoked, about $0.0000 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.