A command that changes Claude Code's AI provider to Z.AI and sets the listed Z.AI models and API endpoint.

Use it to resolve a Z.AI key from supported settings or an argument, then update Claude Code's provider configuration.

It avoids manually finding the API key and editing each provider setting when switching services.

zai — Command by kossakovsky

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/kossakovsky/cc-plugins/zai

Clone the repo

git clone --depth 1 https://github.com/kossakovsky/cc-plugins

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 456 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.

Model	Per session	Once invoked
Fable 5	$0.00006	$0.00456
Opus 5	$0.00003	$0.00228
Sonnet 5	$0.00001	$0.00091
Haiku 4.5	$0.00001	$0.00046

Measured yesterday against content hash 4eb4dbff8b89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

zai 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 yesterday.

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.

c. Read `~/.claude/settings.json` — if `env.ANTHROPIC_AUTH_TOKEN` exists and `env.ANTHROPIC_BASE_URL` contains `z.ai`, reuse the existing key

plugins/switch-provider/commands/zai.md · 43 lines

What it actually says

Switch to Z.AI

Switch Claude Code to use Z.AI as the AI provider.

Provider Config

ANTHROPIC_BASE_URL: https://api.z.ai/api/anthropic
ANTHROPIC_DEFAULT_OPUS_MODEL: glm-5
ANTHROPIC_DEFAULT_SONNET_MODEL: glm-4.7
ANTHROPIC_DEFAULT_HAIKU_MODEL: glm-4.5-air
ANTHROPIC_SMALL_FAST_MODEL: glm-4.5-air

Steps

Resolve API key (in order of priority): a. If an argument was provided, use it as the API key b. Read ~/.claude/provider-keys.json — if it exists and has a zai key, use it c. Read ~/.claude/settings.json — if env.ANTHROPIC_AUTH_TOKEN exists and env.ANTHROPIC_BASE_URL contains z.ai, reuse the existing key d. If no key found, ask the user to provide their Z.AI API key
Read ~/.claude/settings.json using the Read tool

Update the env section with:

{
  "ANTHROPIC_AUTH_TOKEN": "<resolved-api-key>",
  "ANTHROPIC_BASE_URL": "https://api.z.ai/api/anthropic",
  "ANTHROPIC_DEFAULT_OPUS_MODEL": "glm-5",
  "ANTHROPIC_DEFAULT_SONNET_MODEL": "glm-4.7",
  "ANTHROPIC_DEFAULT_HAIKU_MODEL": "glm-4.5-air",
  "ANTHROPIC_SMALL_FAST_MODEL": "glm-4.5-air"
}

Write the updated settings back to ~/.claude/settings.json
Confirm the switch and tell the user: Restart Claude Code to apply changes.

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.

yesterday First seen · 43 lines · 6 tokens per session scan B 4eb4dbff8b89

Subscribe to this mod's changes

zai is a command published in the GitHub repository kossakovsky/cc-plugins (3 stars, last pushed 5mo ago), licensed MIT. It adds 6 tokens to every session and 456 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.

Backend and APIs

zai

Getting it into your agent

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

What it actually says

Switch to Z.AI

Provider Config

Steps

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement