agentmods.dev

vertex

vertex is a command for coding agents from sivang/sivan-claude-plugins. It costs 6 tokens per session (301 once invoked), scanned B, original, MIT.

A command for switching Claude to use Vertex AI, Google's cloud service for running AI models.

In plain words
What is it for?
It is for activating Vertex AI when configuration exists, guiding setup when it does not, and switching back to Anthropic when requested.
Why use it?
It handles the activation flow and reports when setup, a provider choice, or an error needs attention.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the vertex-ai-provider plugin — 5 commands shipped together

not rated 1 7mo ago B scan 6 tokens original MIT
View the source file sivang/sivan-claude-plugins
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/sivang/sivan-claude-plugins/vertex
Clone the repo
git clone --depth 1 https://github.com/sivang/sivan-claude-plugins

Or install vertex-ai-provider, the plugin that ships this one along with the rest of its 5 commands.

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.

agentmods badge for vertex

README.md
[![agentmods](https://agentmods.dev/badge/commands/sivang/sivan-claude-plugins/vertex.svg)](https://agentmods.dev/commands/sivang/sivan-claude-plugins/vertex)
Your own site
<a href="https://agentmods.dev/commands/sivang/sivan-claude-plugins/vertex"><img src="https://agentmods.dev/badge/commands/sivang/sivan-claude-plugins/vertex.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 301 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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.

ModelPer sessionOnce invoked
Fable 5 $0.00006 $0.00301
Opus 5 $0.00003 $0.00151
Sonnet 5 $0.00001 $0.00060
Haiku 4.5 $0.00001 $0.00030

Measured 4d ago against content hash 801ec066cc41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

vertex scanned grade B 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Current state: !`cat ~/.claude/vertex-provider/state.json 2>/dev/null || echo '{"active":false}'`
vertex-ai-provider/commands/vertex.md · 35 lines

What it actually says

Context

  • Current state: !cat ~/.claude/vertex-provider/state.json 2>/dev/null || echo '{"active":false}'
  • Config exists: !test -f ~/.claude/vertex-provider.json && echo "yes" || echo "no"

Your Task

Activate the Vertex AI provider:

  1. If config doesn't exist, tell the user to run /vertex setup first

  2. Run the activation script and capture output:

node "${CLAUDE_PLUGIN_ROOT}/lib/cli/activate.js"

  1. If exit code is 2 (needs prompt): Parse the JSON output and use AskUserQuestion to present options:

    • Extract the reason, question, and options from the JSON
    • Present to user with AskUserQuestion
    • Based on selection:
      • If "anthropic": Run node "${CLAUDE_PLUGIN_ROOT}/lib/cli/deactivate.js" to switch
      • If "retry": Re-run the activation script
      • If "cancel": Tell user they remain on current provider
    • If selected provider needs setup, guide them through it

  2. If exit code is 0: Confirm Vertex AI is now active

  3. If exit code is 1: Show the error message to the user

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.

  1. 4d ago First seen · 35 lines · 6 tokens per session scan B 801ec066cc41

Subscribe to this mod's changes

vertex is a command published in the GitHub repository sivang/sivan-claude-plugins (1 stars, last pushed 7mo ago), licensed MIT. It adds 6 tokens to every session and 301 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AIclaude-codeclaude-code-pluginclaude-pluginsdeveloper-tools
Related

Other commands, from other repositories

prompt

Create or optimize prompts using best practices.

fusengine/agents · 7 tokens

format-converter

Convert between data formats (JSON, CSV, YAML, XML, TOML, Excel). Bidirectional conversion with schema preservation and intelligent type handling.

sigistry/marketplace · 29 tokens

validate

Mechanically validate the sonu plugin repo before a PR — manifest sync, YAML frontmatter, shell-fence syntax, named-source and AI-attribution scans, cross-reference integrity, skill reachability. Only meaningful inside the claude-plugins repo; in any other repo, say so and stop.

PrabhdeepSingh/claude-plugins · 60 tokens

build

Sequence decide → build → hand back for any feature or fix. Triage the change, run design-tree in plan mode (with you as the approval gate — skipped when /sonu:factory routes a ticket whose spec you already approved), build test-first under code-standards, then surface the riskiest parts before handing back to…

PrabhdeepSingh/claude-plugins · 105 tokens

briefing-claude

Use when Claude keeps building the wrong UI and you are re-rolling prompts. How to write the brief, which references and constraints to give, how to iterate instead of starting over, and how to spot when it is guessing.

imsaif/design-with-claude · 46 tokens

index

Index this repository for local RAG search, then report which rung it is on — descriptions still to write, a promotion to apply, or nothing left.

skymanbp/rag-your-code · 31 tokens