Agent skill · Audited from source

Vellum Terminal Sessions

skill · vellum-ai/vellum-assistantMIT licenceAudited 14 Oct 2026 · source 19bc86343b63

★ 1,425pushed 1 day agoversion 0.2
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 19bc863
1,425repo stars · whole vellum-ai/vellum-assistant

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 19bc86343b63 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Manage persistent tmux terminal sessions: create, read, write to, list, and close named shell sessions. For Claude Code or Codex, use the ACP skill instead.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Vellum Terminal Sessions (vellum-ai/vellum-assistant)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/vellum-ai/vellum-terminal-sessions

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium5 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS5
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (5)

Audit 0.4.1 · source sha 19bc86343b63 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishervellum-ai GitHub organizationOwner of the repository this skill is read from
  • Source foldervellum-ai/vellum-assistant/skills/vellum-terminal-sessionsThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict19bc86343b63A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Manage persistent tmux terminal sessions: create, read, write to, list, and close named shell sessions. For Claude Code or Codex, use the ACP skill instead.

---
name: vellum-terminal-sessions
description: "Manage persistent tmux terminal sessions: create, read, write to, list, and close named shell sessions. For Claude Code or Codex, use the ACP skill instead."
compatibility: "Sandbox mode works without any host dependencies. Host mode requires tmux installed on the user's machine. Works on macOS and Linux."
metadata:
  emoji: "🖥️"
  author: vellum-ai
  version: "0.2"
  vellum:
    category: "system"
    display-name: "Terminal Sessions"
    activation-hints:
      - "User asks about their running terminal sessions or processes"
      - "User wants to monitor a long-running command or run something in a persistent shell"
      - "User mentions tmux or terminal management"
      - "User wants to orchestrate multiple CLI processes in parallel"
    avoid-when:
      - "Setting up, authenticating, or running Claude Code or Codex: the ACP skill owns those agents"
      - "A simple one-shot command that host_bash handles fine"
      - "The user is asking about shell scripting in general, not session management"
---

## Overview

This skill manages **persistent terminal sessions** via tmux. Two modes:

|                       | Sandbox Mode                                  | Host Mode                                                           |
| --------------------- | --------------------------------------------- | ------------------------------------------------------------------- |
| **Where tmux runs**   | In the assistant's sandbox                    | On the user's host machine                                          |
| **How user connects** | `vellum terminal attach <session-name>`       | User opens their own terminal                                       |
| **Assistant access**  | Direct (`bash` tool)                          | Via `host_bash`                                                     |
| **Best for**          | Long-running builds, servers, always-on tasks | Work needing host access (e.g. SwiftUI builds, host-local services) |

**Default:** Use **Sandbox Mode** unless the task specifically requires host access. Details: [sandbox-sessions.md](references/sandbox-sessions.md) · [host-sessions.md](references/host-sessions.md) · [tmux-best-practices.md](references/tmux-best-practices.md)

## Prerequisites

**Sandbox Mode:** No setup needed — tmux is available in the sandbox.

**Host Mode:** Requires tmux on the host — see [host-sessions.md](references/host-sessions.md).

## Workflow: Orchestrating Multiple Sessions

- **List** all sessions: `tmux list-sessions` to get names and current commands
- **Read** each: `tmux capture-pane -t NAME -p -S -50` (30-50 lines is usually enough)
- **Summarize** before acting: "Build done, tests at 73%, deploy waiting for confirmation"
- **Act** on the user's instructions

Excerpt, first 2,813 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 19bc863

Download folder ↗
git clone https://github.com/vellum-ai/vellum-assistant
git -C vellum-assistant checkout 19bc86343b63

The author documents no install command, so this uses the repository directly. Our verdict covers commit 19bc86343b63 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 19bc86343b63

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/vellum-ai/vellum-terminal-sessions/badge.svg)](https://modelsatlas.com/skills/vellum-ai/vellum-terminal-sessions/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/vellum-ai/vellum-terminal-sessions/badge.svg)](https://modelsatlas.com/skills/vellum-ai/vellum-terminal-sessions/)

Questions about Vellum Terminal Sessions

What does the Vellum Terminal Sessions skill do?
An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.
Is Vellum Terminal Sessions safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Vellum Terminal Sessions access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Vellum Terminal Sessions work with?
Its documentation mentions claude-code and codex. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (19bc86343b63), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.