Agent skill

Vopen

by vlinx-io in vlinx-io/VelaTerm

Open a file or URL in the vlx-term center pane (mirrors the vopen command).

MITAuto-check passed

Install Vopen

skills CLI
$ npx skills add vlinx-io/VelaTerm --skill vopen -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vlinx-io/VelaTerm vopen --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vlinx-io/VelaTerm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/vopen .claude/skills/vopen && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vopen
GitHub stars
270
Token cost
~697 tokens
SKILL.md length
344 words
Files
1
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

Open a file or URL in the vlx-term center pane (mirrors the vopen command).

  • Works in 3 steps: Resolve the user input into concrete paths → Run the command → Report back to the user
  • The user explicitly invokes /vopen
  • SKILL.md covers Step 1: Resolve the user input…, Step 2: Run the command, Step 3: Report back to the user and Notes
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Vopen is an agent skill from vlinx-io/VelaTerm. Open a file or URL in the vlx-term center pane (mirrors the vopen command). Markdown opens in a WYSIWYG editor, images in the built-in image viewer, other files in the source-code editor (with automatic syntax highlighting by language), and http/https URLs in a built-in browser tab. Only use when the user explicitly invokes /vopen or $vopen; never auto-trigger. Available only inside vlx-term-hosted local sessions.

Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: VelaTerm = Codex + iTerm2, The Best ADE for AI Coding. The licence is MIT.

When your agent uses it

  • The user explicitly invokes /vopen
  • Never auto-trigger

Example prompts

  • “/vopen”

Requirements

  • Pre-approved tools (allowed-tools): Bash(vopen:*)

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Resolve the user input into concrete paths
  2. Run the command
  3. Report back to the user

What it can do on your machine

Read from SKILL.md and the folder at commit 98b5f2f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(vopen:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vopen loads about 697 tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 344 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~106
When it runs · the whole SKILL.md, loaded when a task matches
~697

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vlinx-io/VelaTerm at commit 98b5f2f, republished under its MIT licence (© vlinx-io). 344 words, ~697 tokens.

Download SKILL.mdSave it as .claude/skills/vopen/SKILL.md (or your agent's skills folder).
name
vopen
description
Open a file or URL in the vlx-term center pane (mirrors the `vopen` command). Markdown opens in a WYSIWYG editor, images in the built-in image viewer, other files in the source-code editor (with automatic syntax highlighting by language), and http/https URLs in a built-in browser tab. Only use when the user explicitly invokes /vopen or $vopen; never auto-trigger. Available only inside vlx-term-hosted local sessions.
allowed-tools
Bash(vopen:*)
argument-hint
<file|url>...
disable-model-invocation
true

/vopen

The user explicitly invoked /vopen (Claude) or $vopen (Codex) to request opening a file or URL in the vlx-term center pane, with exactly the same effect as typing vopen <file> in the terminal: it opens a document tab in the center pane, routed automatically by type (markdown WYSIWYG / image viewer / code editor with syntax highlighting), while http/https URLs open a built-in browser tab. The document tab sits alongside the terminal tabs and won't displace the current session.

User input:

$ARGUMENTS

Step 1: Resolve the user input into concrete paths

  • What the user gives may be a literal path or URL, or a reference (e.g. "the file I just edited," "the architecture doc") — resolve references into real file paths from the current conversation context; when unsure, ask first rather than guessing a path to open.
  • Multiple items can be opened at once; resolve each one.
  • Always convert to an absolute path before passing it to the command (the Bash tool's working directory isn't necessarily the "current directory" the user has in mind; absolute paths are the most reliable). Pass URLs (http/https) through as-is.
  • The file must already exist; vopen only accepts regular files, not directories.

Step 2: Run the command

Run vopen from PATH (each path/URL as a separate argument; mind escaping of spaces and other special characters):

bash
vopen <absolute path or url>...

On success it prints a confirmation for each opened item; on failure (file doesn't exist or isn't a regular file) it exits non-zero and reports which file on stderr.

Step 3: Report back to the user

On success, give a one-line summary: "Opened in vlx-term: <file name>"; on failure, report the failed file and the reason honestly.

Notes

  • Must run inside a vlx-term-hosted local session: it relies on the injected VLX_* environment variables and the vopen script on PATH; if missing it reports "not inside a vlx-term session" — in that case just tell the user this skill is only available inside vlx-term sessions, and don't try other ways to open it.
  • Not available inside claude-remote remote sessions (a remote can't reach the local machine's hook port).

© vlinx-io, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/vopen of vlinx-io/VelaTerm.

Open the folder on GitHubat commit 98b5f2f

Compare with similar skills

Vopen next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vopen compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vopen this skillvlinx-io/VelaTerm270—~697Automated safety check: PassMIT
Terms Of Servicethedaviddias/Front-End-Checklist74k—~585Automated safety check: PassMIT
Command Center UIsickn33/agentic-awesome-skills47k1 repos~3.1kAutomated safety check: PassMIT
Ontology Term ResolutionK-Dense-AI/scientific-agent-skills48k1 repos~3.6kAutomated safety check: NotesMIT
GCP Application Design Center Deploygoogle/skills21k—~4.4kAutomated safety check: PassApache-2.0
Search Term Miningirinabuht12-oss/marketing-skills3.9k—~646Automated safety check: PassNone

Similar skills

  • Terms Of Service

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing whether a website or web application has a visible Terms of Service link accessible from every page.

    74k GitHub stars~585 tokensUpdated 2 days ago
    Legal & ComplianceAuto-check passed
  • Command Center UI

    sickn33/agentic-awesome-skills

    Web and App implementation guide for Command Center UI. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~3.1k tokens
    MobileAuto-check passed
  • Ontology Term Resolution

    K-Dense-AI/scientific-agent-skills

    Resolves free-text scientific labels to ontology term IDs and validates existing CURIEs against the EBI Ontology Lookup Service (OLS4).

    48k GitHub starsUsed in 1 repo~3.6k tokens
    Research & ScienceAuto-check: notes
  • Designs GCP infrastructure as local Terraform, validates and scans it against best practices, then imports it to Application Design Center for deployment and troubleshooting.

    21k GitHub stars~4.4k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Search Term Mining

    irinabuht12-oss/marketing-skills

    Analyzes your search term reports across all campaigns and surfaces high-intent terms you're not bidding on yet.

    3.9k GitHub stars~646 tokensUpdated 14 days ago
    Marketing & SEOAuto-check passed
  • Long-Term Compounding Decisions

    kangarooking/cangjie-skill

    Helps you judge whether to commit long-term to a partner, project or relationship by testing for compounding value, trust and reputation.

    11k GitHub stars~681 tokensUpdated 6 days ago
    Business, Finance & HRAuto-check passed

More from vlinx-io/VelaTerm

All 26 skills in this repo
  • Assess Patch Risk

    vlinx-io/VelaTerm

    Assess an immutable patch artifact's program impact, regression risk, and auto-merge eligibility.

    270 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Vspawn

    vlinx-io/VelaTerm

    Explicitly spawn a standalone child session under the current vlx-term session, passing the task in as its first message (mirrors spawntask).

    270 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Deep Security Scan

    vlinx-io/VelaTerm

    A skill your agent uses when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide or scoped-path Codex Security scan.

    270 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed
  • Define Security Policy

    vlinx-io/VelaTerm

    Define, review, or update SECURITY.md guidance for a repository or component.

    270 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Track Findings

    vlinx-io/VelaTerm

    Track validated Codex Security findings in Linear, Jira, GitHub issues, or draft GitHub security advisories.

    270 GitHub stars~5.1k tokensUpdated yesterday
    Auto-check passed
  • Verify Fix

    vlinx-io/VelaTerm

    Use only when the user explicitly requests verification that a security fix remediates a reported vulnerability.

    270 GitHub stars~757 tokensUpdated yesterday
    Auto-check passed

Questions about Vopen

What does Vopen do?

Open a file or URL in the vlx-term center pane (mirrors the vopen command). Vopen is an agent skill from vlinx-io/VelaTerm. Open a file or URL in the vlx-term center pane (mirrors the vopen command).

When should I use Vopen?

Vopen fits situations like: the user explicitly invokes /vopen; never auto-trigger.

How do I install Vopen in Claude Code?

Run `npx skills add vlinx-io/VelaTerm --skill vopen -a claude-code`. Or copy the skill folder (skills/vopen in vlinx-io/VelaTerm) into .claude/skills/vopen in your project. Claude Code loads it when a task matches its description.

How do I install Vopen in Codex?

Run `npx skills add vlinx-io/VelaTerm --skill vopen -a codex`. Or copy the skill folder (skills/vopen in vlinx-io/VelaTerm) into .agents/skills/vopen in your project. Codex loads it when a task matches its description.

Can I use Vopen in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vlinx-io/VelaTerm --skill vopen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vopen, .gemini/skills/vopen, .github/skills/vopen and .opencode/skills/vopen in your project.

What does Vopen need to run?

SKILL.md names no scripts, command-line tools or credentials: Vopen is instructions for the agent only. Its frontmatter pre-approves these tools: Bash(vopen:*).

Does Vopen access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vopen safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vopen use?

Vopen is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vopen use?

About 697 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vopen?

Skills that share tags, products or a category with Vopen: Terms Of Service (thedaviddias/Front-End-Checklist, 74k stars), Command Center UI (sickn33/agentic-awesome-skills, 47k stars), Ontology Term Resolution (K-Dense-AI/scientific-agent-skills, 48k stars) and GCP Application Design Center Deploy (google/skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vopen?

vlinx-io (a GitHub user) maintains it in vlinx-io/VelaTerm, which has 270 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 7, 2026.

Source: vlinx-io/VelaTerm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.