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.
git clone --depth 1 https://github.com/ankitaa186/host-terminal-mcpWrote 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.
[](https://agentmods.dev/commands/ankitaa186/host-terminal-mcp/permissions)<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.
<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>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 5.5 | $0.00003 | $0.00233 |
| Sonnet 5.5 | $0.00002 | $0.00117 |
| Haiku 4.5 | $0.00001 | $0.00058 |
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 2mo 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 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
allowlistis the default and recommended for productionaskmode approvals are session-only (not persisted)allow_allshould 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:
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.
- 2mo ago First seen · 105 lines · 8 tokens per session scan C 1cdd24466985
permissions is a command published in the GitHub repository ankitaa186/host-terminal-mcp (0 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 8 tokens to every session and 583 once invoked, about $0.0000 per session on Opus 5.5. 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.
permissions compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| permissionsankitaa186/host-terminal-mcp | Command | 0 | 8mo ago | Apache-2.0 | C | 8 | Claude Code |
| checklistgithub/spec-kit | Command | 150k | 3d ago | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 150k | 3d ago | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 150k | 3d ago | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 150k | 3d ago | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 150k | 3d ago | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 150k | 3d ago | MIT | A | 14 | Claude Code |