A command that switches a Claude setup from Google Vertex AI back to Anthropic's API. It runs the provider-change script and handles setup prompts or errors.

Use it to deactivate Vertex AI and return to Anthropic's service. It can also tell you when an Anthropic API key is needed or when a choice is required.

It helps when you no longer want to use Vertex AI, or when the current provider must be changed for configuration or access reasons.

anthropic — Command for Claude Code by sivang/sivan-claude-plugins

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add sivang/sivan-claude-plugins

Claude Code

/plugin install vertex-ai-provider

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/sivang/sivan-claude-plugins/anthropic/github.svg)](https://agentmods.dev/commands/sivang/sivan-claude-plugins/anthropic)

Your own site

<a href="https://agentmods.dev/commands/sivang/sivan-claude-plugins/anthropic"><img src="https://agentmods.dev/badge/commands/sivang/sivan-claude-plugins/anthropic/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/sivang/sivan-claude-plugins/anthropic"><img src="https://agentmods.dev/badge/commands/sivang/sivan-claude-plugins/anthropic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 267 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 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	$0.00013	$0.00267
Opus 5.5	$0.00005	$0.00107
Sonnet 5.5	$0.00003	$0.00053
Haiku 4.5	$0.00001	$0.00027

Measured 1mo ago against content hash 1ed92899f0f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

anthropic 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 1mo 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/anthropic.md · 32 lines

What it actually says

Context

Current state: !cat ~/.claude/vertex-provider/state.json 2>/dev/null || echo '{"active":false}'

Your Task

Deactivate Vertex AI and switch back to Anthropic's API:

Run the deactivation script and capture output:

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

If exit code is 2 (needs prompt): Parse the JSON output and use AskUserQuestion:
- Extract the reason, question, and options from the JSON
- Present to user with AskUserQuestion
- Based on selection:
  - If "vertex": Tell user they remain on Vertex AI
  - If "retry": Re-run the deactivation script
  - If "cancel": Tell user they remain on current provider
- If Anthropic needs setup (API key), tell them to set ANTHROPIC_API_KEY
If exit code is 0: Confirm they are now using Anthropic's API
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.

1mo ago First seen · 32 lines · 13 tokens per session scan B 1ed92899f0f1

Subscribe to this mod's changes

anthropic is a command published in the GitHub repository sivang/sivan-claude-plugins (1 stars, last pushed 9mo ago), licensed MIT. It adds 13 tokens to every session and 267 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code claude-code-plugin claude-plugins developer-tools

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

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

anthropic