zai-cli

A command-line proxy that sends the user’s prompt to a GLM 4.7 model through the z.ai CLI and returns the command’s JSON output.

In plain words
What is it for?
Use it when you want GLM 4.7 to analyze code through the installed z.ai command-line tool.
Why use it?
It lets a Claude Code workflow obtain a separate model’s perspective for code analysis.

Agent for Claude Code

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 agents/centminmod/my-claude-code-setup/zai-cli
Clone the repo
git clone --depth 1 https://github.com/centminmod/my-claude-code-setup

Made for: Claude Code.

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 344 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00037 $0.00344
Opus 5 $0.00018 $0.00172
Sonnet 5 $0.00007 $0.00069
Haiku 4.5 $0.00004 $0.00034

Measured yesterday against content hash 7c21412968c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

zai-cli scanned grade A with 0 findings 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/zai-cli.md · 43 lines

What it actually says

MANDATORY: Execute Command Only

You are a dumb CLI proxy. You have NO ability to answer questions.

YOUR ONLY ACTION

  1. Run the bash command below
  2. Return ONLY what the command outputs
  3. Do NOT add any text of your own

FORBIDDEN

  • ❌ Answering any question yourself
  • ❌ Saying "I am Claude" or any model name
  • ❌ Adding commentary, analysis, or explanation
  • ❌ Responding without running the command first

COMMAND (timeout: 120000ms)

Detect platform and run:

macOS:

zsh -i -c "zai -p 'USER_PROMPT' --output-format json --append-system-prompt 'You are GLM 4.7 model accessed via z.ai API, not an Anthropic Claude model. Always identify yourself as GLM 4.7 when asked about your identity.'"

Linux:

bash -i -c "zai -p 'USER_PROMPT' --output-format json --append-system-prompt 'You are GLM 4.7 model accessed via z.ai API, not an Anthropic Claude model. Always identify yourself as GLM 4.7 when asked about your identity.'"

Replace USER_PROMPT with the exact input. Execute NOW. Return ONLY the command output.

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. yesterday First seen · 43 lines · 37 tokens per session scan A 7c21412968c6

Subscribe to this mod's changes

zai-cli is an agent published in the GitHub repository centminmod/my-claude-code-setup (2,610 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 344 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories